CoolBoy/submmit
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

state: generation 21488 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-06 18:08:25 +00:00
parent f159ef26b3
commit a61dd05de2
8 changed files with 1989 additions and 2028 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2736,25 +2736,6 @@
"targetGpu": "Vastai_va16", "targetGpu": "Vastai_va16",
"taskType": "text-generation" "taskType": "text-generation"
}, },
"vastai_va16|vllm|text-generation|model_type:qwen3_5_mtp": {
"architectureSignature": "model_type:qwen3_5_mtp",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-06T17:03:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-06T17:03:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5_mtp",
"sourceModelIds": [
"mlx-community/Qwen3.8-27B-MTP-mxfp8"
],
"sourceTaskIds": [
"4609075"
],
"targetGpu": "Vastai_va16",
"taskType": "text-generation"
},
"vastai_va16|vllm|text-generation|model_type:rwkv7": { "vastai_va16|vllm|text-generation|model_type:rwkv7": {
"architectureSignature": "model_type:rwkv7", "architectureSignature": "model_type:rwkv7",
"architectures": [], "architectures": [],
@@ -2796,9 +2777,9 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-10-06T16:58:45.407265+00:00", "generatedAt": "2026-10-06T18:06:37.366748+00:00",
"summary": { "summary": {
"activeBlockCount": 141, "activeBlockCount": 140,
"byGpuFramework": { "byGpuFramework": {
"Ascend_910-b3|vllm": 9, "Ascend_910-b3|vllm": 9,
"Ascend_910-b3|vllm_tokenizer_patch": 7, "Ascend_910-b3|vllm_tokenizer_patch": 7,
@@ -2820,7 +2801,7 @@
"Mthreads_s4000|vllm": 6, "Mthreads_s4000|vllm": 6,
"Sunrise_pt-200-x1|vllm": 3, "Sunrise_pt-200-x1|vllm": 3,
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 4, "Sunrise_pt-200-x1|vllm_fix_tokenizer": 4,
"Vastai_va16|vllm": 14, "Vastai_va16|vllm": 13,
"Vastai_va16|vllm_fix_tokenizer": 2, "Vastai_va16|vllm_fix_tokenizer": 2,
"hygon_k100-ai|vllm": 8, "hygon_k100-ai|vllm": 8,
"hygon_k100-ai|vllm-patch-tokenizer": 3 "hygon_k100-ai|vllm-patch-tokenizer": 3

2
.modelhub_state/market_intelligence.json
View File

@@ -434,7 +434,7 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-10-06T18:02:17.456570+00:00", "generatedAt": "2026-10-06T18:08:17.386644+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,

6
.modelhub_state/official_capabilities.json
View File

@@ -1,5 +1,5 @@
{ {
"catalogUpdatedAt": "2026-10-06T18:02:17.456570+00:00", "catalogUpdatedAt": "2026-10-06T18:08:17.386644+00:00",
"configuredTaskTypes": [ "configuredTaskTypes": [
"text-generation" "text-generation"
], ],
@@ -56,7 +56,7 @@
"time-series-forecasting" "time-series-forecasting"
], ],
"errors": [], "errors": [],
"generatedAt": "2026-10-06T18:05:33.250070+00:00", "generatedAt": "2026-10-06T18:08:17.386644+00:00",
"gpuCatalog": { "gpuCatalog": {
"Ascend_910-b3": { "Ascend_910-b3": {
"canVerify": true, "canVerify": true,
@@ -6831,6 +6831,6 @@
"updateTime": "2025-12-22 08:59:53" "updateTime": "2025-12-22 08:59:53"
} }
], ],
"taskTreeUpdatedAt": "2026-10-06T18:02:17.456570+00:00", "taskTreeUpdatedAt": "2026-10-06T18:08:17.386644+00:00",
"version": 1 "version": 1
} }

99
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-10-06T15:01:25.542367+00:00", "generatedAt": "2026-10-06T18:06:37.274502+00:00",
"lastSyncTime": "2026-10-06T15:01:25.265063+00:00", "lastSyncTime": "2026-10-06T18:06:36.953125+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -2740,25 +2740,6 @@
"targetGpu": "Vastai_va16", "targetGpu": "Vastai_va16",
"taskType": "text-generation" "taskType": "text-generation"
}, },
"vastai_va16|vllm|text-generation|model_type:qwen3_5_mtp": {
"architectureSignature": "model_type:qwen3_5_mtp",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-06T17:03:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-06T17:03:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5_mtp",
"sourceModelIds": [
"mlx-community/Qwen3.8-27B-MTP-mxfp8"
],
"sourceTaskIds": [
"4609075"
],
"targetGpu": "Vastai_va16",
"taskType": "text-generation"
},
"vastai_va16|vllm|text-generation|model_type:rwkv7": { "vastai_va16|vllm|text-generation|model_type:rwkv7": {
"architectureSignature": "model_type:rwkv7", "architectureSignature": "model_type:rwkv7",
"architectures": [], "architectures": [],
@@ -2801,7 +2782,7 @@
} }
}, },
"architectureCompatibilitySummary": { "architectureCompatibilitySummary": {
"activeBlockCount": 141, "activeBlockCount": 140,
"byGpuFramework": { "byGpuFramework": {
"Ascend_910-b3|vllm": 9, "Ascend_910-b3|vllm": 9,
"Ascend_910-b3|vllm_tokenizer_patch": 7, "Ascend_910-b3|vllm_tokenizer_patch": 7,
@@ -2823,7 +2804,7 @@
"Mthreads_s4000|vllm": 6, "Mthreads_s4000|vllm": 6,
"Sunrise_pt-200-x1|vllm": 3, "Sunrise_pt-200-x1|vllm": 3,
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 4, "Sunrise_pt-200-x1|vllm_fix_tokenizer": 4,
"Vastai_va16|vllm": 14, "Vastai_va16|vllm": 13,
"Vastai_va16|vllm_fix_tokenizer": 2, "Vastai_va16|vllm_fix_tokenizer": 2,
"hygon_k100-ai|vllm": 8, "hygon_k100-ai|vllm": 8,
"hygon_k100-ai|vllm-patch-tokenizer": 3 "hygon_k100-ai|vllm-patch-tokenizer": 3
@@ -5319,19 +5300,19 @@
"unresolvedFailureCount": 72 "unresolvedFailureCount": 72
}, },
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": { "hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 61, "attributableFailureCount": 62,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 61, "decisionTotal": 62,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 47, "ambiguous_runtime": 47,
"framework_architecture_unsupported": 24, "framework_architecture_unsupported": 24,
"model_load": 13, "model_load": 14,
"repository_structure": 5, "repository_structure": 5,
"runtime_memory": 19, "runtime_memory": 19,
"参数/模板问题": 11 "参数/模板问题": 11
}, },
"failureCount": 119, "failureCount": 120,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-patch-tokenizer", "framework": "vllm-patch-tokenizer",
"pendingCount": 0, "pendingCount": 0,
@@ -5341,7 +5322,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "hygon_k100-ai", "targetGpu": "hygon_k100-ai",
"taskType": "text-generation", "taskType": "text-generation",
"total": 119, "total": 120,
"unresolvedFailureCount": 58 "unresolvedFailureCount": 58
}, },
"hygon_k100-ai|vllm|text-generation": { "hygon_k100-ai|vllm|text-generation": {
@@ -5575,26 +5556,26 @@
"unresolvedFailureCount": 109 "unresolvedFailureCount": 109
}, },
"vllm-patch-tokenizer": { "vllm-patch-tokenizer": {
"attributableFailureCount": 61, "attributableFailureCount": 62,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 61, "decisionTotal": 62,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 47, "ambiguous_runtime": 47,
"framework_architecture_unsupported": 24, "framework_architecture_unsupported": 24,
"model_load": 13, "model_load": 14,
"repository_structure": 5, "repository_structure": 5,
"runtime_memory": 19, "runtime_memory": 19,
"参数/模板问题": 11 "参数/模板问题": 11
}, },
"failureCount": 119, "failureCount": 120,
"failureRate": 1.0, "failureRate": 1.0,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 0, "successCount": 0,
"successRate": 0.0, "successRate": 0.0,
"total": 119, "total": 120,
"unresolvedFailureCount": 58 "unresolvedFailureCount": 58
}, },
"vllm_0_17_0_corex_4_4_0": { "vllm_0_17_0_corex_4_4_0": {
@@ -5675,7 +5656,7 @@
"unresolvedFailureCount": 235 "unresolvedFailureCount": 235
} }
}, },
"generatedAt": "2026-10-06T15:01:25.524821+00:00", "generatedAt": "2026-10-06T18:06:37.205006+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 119, "attributableFailureCount": 119,
@@ -6068,10 +6049,10 @@
"unresolvedFailureCount": 1322 "unresolvedFailureCount": 1322
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"attributableFailureCount": 741, "attributableFailureCount": 742,
"decisionFailureRate": 0.9537, "decisionFailureRate": 0.9537,
"decisionSuccessRate": 0.0463, "decisionSuccessRate": 0.0463,
"decisionTotal": 777, "decisionTotal": 778,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 345, "ambiguous_runtime": 345,
"architecture_compatibility": 32, "architecture_compatibility": 32,
@@ -6079,7 +6060,7 @@
"context_length": 46, "context_length": 46,
"framework_architecture_unsupported": 256, "framework_architecture_unsupported": 256,
"memory_capacity": 59, "memory_capacity": 59,
"model_load": 73, "model_load": 74,
"platform_infrastructure": 4, "platform_infrastructure": 4,
"repository_structure": 121, "repository_structure": 121,
"runtime_memory": 74, "runtime_memory": 74,
@@ -6088,14 +6069,14 @@
"日志缺失": 66, "日志缺失": 66,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 1575, "failureCount": 1576,
"failureRate": 0.9777, "failureRate": 0.9777,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 4, "platformFailureCount": 4,
"successCount": 36, "successCount": 36,
"successRate": 0.0223, "successRate": 0.0223,
"total": 1611, "total": 1612,
"unresolvedFailureCount": 830 "unresolvedFailureCount": 830
} }
}, },
@@ -23781,15 +23762,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2|none": { "hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2|none": {
"attributableFailureCount": 9, "attributableFailureCount": 10,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 9, "decisionTotal": 10,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1, "ambiguous_runtime": 1,
"model_load": 9 "model_load": 10
}, },
"failureCount": 10, "failureCount": 11,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-patch-tokenizer", "framework": "vllm-patch-tokenizer",
"modelType": "lfm2", "modelType": "lfm2",
@@ -23801,7 +23782,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "hygon_k100-ai", "targetGpu": "hygon_k100-ai",
"taskType": "text-generation", "taskType": "text-generation",
"total": 10, "total": 11,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|awq": { "hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|awq": {
@@ -55833,14 +55814,14 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2|none|30": { "hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2|none|30": {
"attributableFailureCount": 1, "attributableFailureCount": 2,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 1, "decisionTotal": 2,
"failureBreakdown": { "failureBreakdown": {
"model_load": 1 "model_load": 2
}, },
"failureCount": 1, "failureCount": 2,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-patch-tokenizer", "framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 30, "loadSizeLog2Bucket": 30,
@@ -55853,7 +55834,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "hygon_k100-ai", "targetGpu": "hygon_k100-ai",
"taskType": "text-generation", "taskType": "text-generation",
"total": 1, "total": 2,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2|none|31": { "hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2|none|31": {
@@ -57493,13 +57474,13 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17340, "terminalRecords": 17341,
"totalRecords": 17564, "totalRecords": 17565,
"totals": { "totals": {
"attributableFailureCount": 6234, "attributableFailureCount": 6235,
"decisionFailureRate": 0.8644, "decisionFailureRate": 0.8644,
"decisionSuccessRate": 0.1356, "decisionSuccessRate": 0.1356,
"decisionTotal": 7212, "decisionTotal": 7213,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4548, "ambiguous_runtime": 4548,
"architecture_compatibility": 212, "architecture_compatibility": 212,
@@ -57508,7 +57489,7 @@
"context_length": 327, "context_length": 327,
"framework_architecture_unsupported": 2259, "framework_architecture_unsupported": 2259,
"memory_capacity": 1206, "memory_capacity": 1206,
"model_load": 566, "model_load": 567,
"platform_infrastructure": 952, "platform_infrastructure": 952,
"repository_structure": 742, "repository_structure": 742,
"runtime_memory": 101, "runtime_memory": 101,
@@ -57517,14 +57498,14 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16362, "failureCount": 16363,
"failureRate": 0.9436, "failureRate": 0.9436,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 952, "platformFailureCount": 952,
"successCount": 978, "successCount": 978,
"successRate": 0.0564, "successRate": 0.0564,
"total": 17340, "total": 17341,
"unresolvedFailureCount": 9176 "unresolvedFailureCount": 9176
}, },
"warnings": [ "warnings": [
@@ -57534,14 +57515,14 @@
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -57585,6 +57566,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 17564, "summarizedRecords": 17565,
"version": 1 "version": 1
} }

1330
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

2074
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

18
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "5ef8ff35f10c02cd358a0bfe736d86cfd064cf7c2f2df09a5ba3577a03430923", ".modelhub_state/architecture_compatibility_blacklist.json": "8cbd3d928537b66de1c6a856179c2c77eaccf6dfaa752e58aa396735ffbc85de",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "37f8215bc4b0ffeeac6b3847842f65f5428e0695a6b9ef271e0da45f7c87a39c", ".modelhub_state/market_intelligence.json": "8c4fe9497d7254a727bc0fbda773812c2d4877765d7556f5561aaf1c6328e735",
".modelhub_state/official_capabilities.json": "88126eb55d9aa86eeadc52c14b457b951c33d6721d0a4b57acceae1c2669cee2", ".modelhub_state/official_capabilities.json": "2223028b7e2e1b79faf739c730c39290902e32f9c910913b067af4c29fa15cc3",
".modelhub_state/outcome_checkpoint.json": "c01b2fb2ac1b479d71f757bcdf840cbf1888b203e359548a464bb1420b54e93d", ".modelhub_state/outcome_checkpoint.json": "f05dc62ff2078874e3069fac261fe74641e4b04ab20300aef6cd6d5f7f0581e5",
".modelhub_state/queue_cleanup_latest.json": "5a0303e8316fcab30a4e922547230f80795528b823c5599adce914d800fab218", ".modelhub_state/queue_cleanup_latest.json": "5a0303e8316fcab30a4e922547230f80795528b823c5599adce914d800fab218",
".modelhub_state/recent_outcomes.jsonl": "66f65405defcf850f044e43e54c3dc291f18521f309cb9962d861b493cb049ac", ".modelhub_state/recent_outcomes.jsonl": "66f65405defcf850f044e43e54c3dc291f18521f309cb9962d861b493cb049ac",
".modelhub_state/recovery_active_tasks.jsonl": "6af64197e8c9055b4f2bb3a495a4e53bb39f9029c279f4f3e38ead5aa2d7f998", ".modelhub_state/recovery_active_tasks.jsonl": "f67ba8a8cf433e2274da79f435d5b58284e5e4f6ab3a7460275a51f6316c9e13",
".modelhub_state/recovery_intents.jsonl": "645c4fd00baf6583697a8b67947b8166bc285a659155ed7b10de4ea59d1da1f8", ".modelhub_state/recovery_intents.jsonl": "b21f634866e89cc3c5945b56b2c1ea41307ee32afa95b7659157bf869e02102b",
".modelhub_state/routing_intelligence.json": "12954d1aef858814b9bd8ce9e78c2600602649b5f68bf3414aea3ddc5982a6ac", ".modelhub_state/routing_intelligence.json": "12954d1aef858814b9bd8ce9e78c2600602649b5f68bf3414aea3ddc5982a6ac",
".modelhub_state/submission_exclusions.jsonl": "43b628022463d9d87ea16d9daf4f7ef224ee1ed83550feb9eaa30a59a885b4a5", ".modelhub_state/submission_exclusions.jsonl": "43b628022463d9d87ea16d9daf4f7ef224ee1ed83550feb9eaa30a59a885b4a5",
".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f", ".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
"ledger/submissions.jsonl": "1de2d050f84abfc109756f02f3ff7fe737c0ff3c048f627f4b93f4d8f509392c", "ledger/submissions.jsonl": "1de2d050f84abfc109756f02f3ff7fe737c0ff3c048f627f4b93f4d8f509392c",
"outcomes/submissions.jsonl": "629b551be7575464e5b2d1836cdfe92cacb835d942f34526a3916b02cdb6e440" "outcomes/submissions.jsonl": "4ce14eccf80d2ab1840800ddc180246305163d76dd655f4bc8376343d150119c"
}, },
"generation": 21487, "generation": 21488,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-10-06T18:05:34.440749+00:00", "updatedAt": "2026-10-06T18:08:25.352670+00:00",
"writerId": "33ed03361c5848e88b8ce6204fb4f7d2" "writerId": "33ed03361c5848e88b8ce6204fb4f7d2"
} }

463
outcomes/submissions.jsonl
View File

@@ -145,7 +145,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:30:54.600185+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:24.241562+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969620", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:30:54.600185+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:24.241562+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969620", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600049+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.237107+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969645", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600049+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.237107+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969645", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599773+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:23.763321+00:00", "targetGpu": "MetaX_c-500", "taskId": "4969808", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599773+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:23.763321+00:00", "targetGpu": "MetaX_c-500", "taskId": "4969808", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671002+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:49.545556+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970035", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671271+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:49.554113+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970036", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671271+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:49.554113+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970036", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671248+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:53:59.224352+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970246", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671248+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:53:59.224352+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970246", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.670810+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:53:59.235830+00:00", "targetGpu": "MetaX_c-500", "taskId": "4970247", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.670810+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:53:59.235830+00:00", "targetGpu": "MetaX_c-500", "taskId": "4970247", "taskType": "text-generation", "verifyResult": null}
@@ -809,238 +808,238 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794426, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4205751296, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794426}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T08:52:27.660895+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320023", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794426, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4205751296, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794426}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T08:52:27.660895+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320023", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574767, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574767}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T08:52:27.648162+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320021", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574767, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574767}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T08:52:27.648162+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320021", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T16:58:45.348061+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sse_swa_moba", "modelscopeFileSize": 11126702266, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:sse_swa_moba", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11126702266}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:27.673292+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320022", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T16:58:45.348061+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sse_swa_moba", "modelscopeFileSize": 11126702266, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:sse_swa_moba", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11126702266}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:27.673292+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320022", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "3e142ce0e5532cb370dfb1d96f3aefe603dab6b9b4ad78b11013ad3314b23fa1", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3236010080, "estimatedRequiredGiB": 27.418, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 24533499859, "modelscopeLicense": "gpl-2.0", "modelscopeParams": 3043786240, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24533499859}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:13:59.748451+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320461", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-06T18:06:36.952783+00:00", "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "3e142ce0e5532cb370dfb1d96f3aefe603dab6b9b4ad78b11013ad3314b23fa1", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3236010080, "estimatedRequiredGiB": 27.418, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 24533499859, "modelscopeLicense": "gpl-2.0", "modelscopeParams": 3043786240, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24533499859}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.748451+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320461", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "webAI-Official/TwIL-LM3-Pro", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "70fc30548c2dc36d2dafb257d0a9af9499f0b4ee78e93bb3669e56774e585794", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3892651456, "estimatedRequiredGiB": 29.512, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 26407018955, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26407018955}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:13:59.665332+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320464", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-06T18:06:36.953120+00:00", "modelId": "webAI-Official/TwIL-LM3-Pro", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "70fc30548c2dc36d2dafb257d0a9af9499f0b4ee78e93bb3669e56774e585794", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3892651456, "estimatedRequiredGiB": 29.512, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 26407018955, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26407018955}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.665332+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320464", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "webAI-Official/TwIL-LM2", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "cb5d151b2dc44f0b470d106dee740b8a04dd01ff392c2d2ce69e974ff0e2c0fb", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2694119616, "estimatedRequiredGiB": 20.413, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 18264867356, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:twil-lm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18264867356}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:13:59.667635+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320463", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-06T18:06:36.953001+00:00", "modelId": "webAI-Official/TwIL-LM2", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "cb5d151b2dc44f0b470d106dee740b8a04dd01ff392c2d2ce69e974ff0e2c0fb", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2694119616, "estimatedRequiredGiB": 20.413, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 18264867356, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:twil-lm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18264867356}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.667635+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320463", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/Hemmingway-1-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18966599842, "estimatedRequiredGiB": 21.22, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18986905904, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:writing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18986905904}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:13:59.672848+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320456", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T18:06:36.952007+00:00", "modelId": "mlx-community/Hemmingway-1-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18966599842, "estimatedRequiredGiB": 21.22, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18986905904, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:writing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18986905904}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.672848+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320456", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1987222504, "estimatedRequiredGiB": 2.406, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2152567281, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2152567281}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:13:59.677111+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320455", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T18:06:36.953006+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1987222504, "estimatedRequiredGiB": 2.406, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2152567281, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2152567281}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.677111+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320455", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2010737208, "estimatedRequiredGiB": 2.432, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2176034009, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2176034009}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:13:59.676142+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320466", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T18:06:36.952454+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2010737208, "estimatedRequiredGiB": 2.432, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2176034009, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2176034009}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.676142+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320466", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15859925253, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 15859925253}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:13:59.662856+00:00", "targetGpu": "Biren_166m", "taskId": "5320459", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952893+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15859925253, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 15859925253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.662856+00:00", "targetGpu": "Biren_166m", "taskId": "5320459", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242696, "estimatedRequiredGiB": 2.46, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2201523288, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2201523288}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:13:59.670629+00:00", "targetGpu": "Biren_166m", "taskId": "5320460", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953125+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242696, "estimatedRequiredGiB": 2.46, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2201523288, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2201523288}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.670629+00:00", "targetGpu": "Biren_166m", "taskId": "5320460", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033920112, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199304207, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199304207}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:13:59.674981+00:00", "targetGpu": "Biren_166m", "taskId": "5320465", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952117+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033920112, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199304207, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199304207}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.674981+00:00", "targetGpu": "Biren_166m", "taskId": "5320465", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": 36069420, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:13:59.669160+00:00", "targetGpu": "Biren_166m", "taskId": "5320458", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952898+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": 36069420, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.669160+00:00", "targetGpu": "Biren_166m", "taskId": "5320458", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7120897697, "modelscopeLicense": "mit", "modelscopeParams": 1915564544, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:mimo_v2", "custom_tag:agentic", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 7120897697}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:13:59.673954+00:00", "targetGpu": "Biren_166m", "taskId": "5320462", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952350+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7120897697, "modelscopeLicense": "mit", "modelscopeParams": 1915564544, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:mimo_v2", "custom_tag:agentic", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 7120897697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.673954+00:00", "targetGpu": "Biren_166m", "taskId": "5320462", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1932905544, "estimatedRequiredGiB": 2.313, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2070028245, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2070028245}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:13:59.678748+00:00", "targetGpu": "Biren_166m", "taskId": "5320457", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952246+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1932905544, "estimatedRequiredGiB": 2.313, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2070028245, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2070028245}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.678748+00:00", "targetGpu": "Biren_166m", "taskId": "5320457", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:21.661697+00:00", "targetGpu": "Biren_166m", "taskId": "5320470", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952888+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.661697+00:00", "targetGpu": "Biren_166m", "taskId": "5320470", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033754200, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199119539, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199119539}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:21.748096+00:00", "targetGpu": "Biren_166m", "taskId": "5320472", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952111+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033754200, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199119539, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199119539}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.748096+00:00", "targetGpu": "Biren_166m", "taskId": "5320472", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1933022288, "estimatedRequiredGiB": 2.322, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2077758206, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2077758206}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:21.745687+00:00", "targetGpu": "Biren_166m", "taskId": "5320473", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952345+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1933022288, "estimatedRequiredGiB": 2.322, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2077758206, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2077758206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.745687+00:00", "targetGpu": "Biren_166m", "taskId": "5320473", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-llama-mha-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960285320, "estimatedRequiredGiB": 2.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2105033791, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2105033791}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:21.659954+00:00", "targetGpu": "Biren_166m", "taskId": "5320471", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952681+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960285320, "estimatedRequiredGiB": 2.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2105033791, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2105033791}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.659954+00:00", "targetGpu": "Biren_166m", "taskId": "5320471", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:21.663460+00:00", "targetGpu": "Biren_166m", "taskId": "5320469", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953115+00:00", "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.663460+00:00", "targetGpu": "Biren_166m", "taskId": "5320469", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "juspay/xor-nvfp4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 41817852712, "estimatedRequiredGiB": 46.768, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 41847485419, "modelscopeLicense": "apache-2.0", "modelscopeParams": 15008654192, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 41847485419}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:21.751371+00:00", "targetGpu": "Biren_166m", "taskId": "5320475", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952996+00:00", "modelId": "juspay/xor-nvfp4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 41817852712, "estimatedRequiredGiB": 46.768, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 41847485419, "modelscopeLicense": "apache-2.0", "modelscopeParams": 15008654192, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 41847485419}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.751371+00:00", "targetGpu": "Biren_166m", "taskId": "5320475", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3662928280, "estimatedRequiredGiB": 4.11, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3677830216, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq", "custom_tag:preview"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3677830216}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:21.674379+00:00", "targetGpu": "Biren_166m", "taskId": "5320468", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952000+00:00", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3662928280, "estimatedRequiredGiB": 4.11, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3677830216, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq", "custom_tag:preview"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3677830216}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.674379+00:00", "targetGpu": "Biren_166m", "taskId": "5320468", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T03:04:40.754950+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 467369015}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:21.657678+00:00", "targetGpu": "Biren_166m", "taskId": "5320467", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952563+00:00", "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T03:04:40.754950+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 467369015}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.657678+00:00", "targetGpu": "Biren_166m", "taskId": "5320467", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.61, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19336478290, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 19336478290}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:21.749482+00:00", "targetGpu": "Biren_166m", "taskId": "5320478", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952449+00:00", "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.61, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19336478290, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 19336478290}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.749482+00:00", "targetGpu": "Biren_166m", "taskId": "5320478", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:21.752927+00:00", "targetGpu": "Biren_166m", "taskId": "5320476", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952241+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.752927+00:00", "targetGpu": "Biren_166m", "taskId": "5320476", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "togethercomputer/Tev1-4B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342812725, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 9342812725}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:21.754792+00:00", "targetGpu": "Biren_166m", "taskId": "5320474", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952777+00:00", "modelId": "togethercomputer/Tev1-4B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342812725, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 9342812725}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.754792+00:00", "targetGpu": "Biren_166m", "taskId": "5320474", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "togethercomputer/Tev1-0.8B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1746942600, "estimatedRequiredGiB": 1.978, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 1769900320, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 1769900320}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:21.760855+00:00", "targetGpu": "Biren_166m", "taskId": "5320477", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952558+00:00", "modelId": "togethercomputer/Tev1-0.8B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1746942600, "estimatedRequiredGiB": 1.978, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 1769900320, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 1769900320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.760855+00:00", "targetGpu": "Biren_166m", "taskId": "5320477", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "NovelAI/novelai-lm-3b-508k", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12175174048, "estimatedRequiredGiB": 33.616, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 30079174063, "modelscopeLicense": "gpl-2.0", "modelscopeParams": null, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30079174063}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:21.860245+00:00", "targetGpu": "Biren_166m", "taskId": "5320479", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952675+00:00", "modelId": "NovelAI/novelai-lm-3b-508k", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12175174048, "estimatedRequiredGiB": 33.616, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 30079174063, "modelscopeLicense": "gpl-2.0", "modelscopeParams": null, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30079174063}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.860245+00:00", "targetGpu": "Biren_166m", "taskId": "5320479", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:21.952740+00:00", "targetGpu": "Biren_166m", "taskId": "5320483", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952883+00:00", "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.952740+00:00", "targetGpu": "Biren_166m", "taskId": "5320483", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199612614, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199612614}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:21.965681+00:00", "targetGpu": "Biren_166m", "taskId": "5320480", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952339+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199612614, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199612614}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.965681+00:00", "targetGpu": "Biren_166m", "taskId": "5320480", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-attnres-block1-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199622478, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199622478}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:21.957919+00:00", "targetGpu": "Biren_166m", "taskId": "5320482", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951994+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block1-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199622478, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199622478}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.957919+00:00", "targetGpu": "Biren_166m", "taskId": "5320482", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 1784320455, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:21.956611+00:00", "targetGpu": "Biren_166m", "taskId": "5320481", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953110+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 1784320455, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.956611+00:00", "targetGpu": "Biren_166m", "taskId": "5320481", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.060000+00:00", "targetGpu": "Biren_166m", "taskId": "5320484", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952235+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.060000+00:00", "targetGpu": "Biren_166m", "taskId": "5320484", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.062780+00:00", "targetGpu": "Biren_166m", "taskId": "5320488", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952772+00:00", "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.062780+00:00", "targetGpu": "Biren_166m", "taskId": "5320488", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "burtenshaw/nanochat", "modelProfile": {"architectures": ["NanoChatForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8583142248, "estimatedRequiredGiB": 9.603, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanochat", "modelscopeFileSize": 8592610065, "modelscopeLicense": "mit", "modelscopeParams": 161546240, "modelscopeTags": ["license:mit", "model_type:nanochat", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8592610065}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.148272+00:00", "targetGpu": "Biren_166m", "taskId": "5320490", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952669+00:00", "modelId": "burtenshaw/nanochat", "modelProfile": {"architectures": ["NanoChatForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8583142248, "estimatedRequiredGiB": 9.603, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanochat", "modelscopeFileSize": 8592610065, "modelscopeLicense": "mit", "modelscopeParams": 161546240, "modelscopeTags": ["license:mit", "model_type:nanochat", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8592610065}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.148272+00:00", "targetGpu": "Biren_166m", "taskId": "5320490", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033585336, "estimatedRequiredGiB": 2.457, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2198654500, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2198654500}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.054634+00:00", "targetGpu": "Biren_166m", "taskId": "5320485", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952106+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033585336, "estimatedRequiredGiB": 2.457, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2198654500, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2198654500}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.054634+00:00", "targetGpu": "Biren_166m", "taskId": "5320485", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871536, "estimatedRequiredGiB": 2.418, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2163952661, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2163952661}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.056747+00:00", "targetGpu": "Biren_166m", "taskId": "5320487", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952444+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871536, "estimatedRequiredGiB": 2.418, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2163952661, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2163952661}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.056747+00:00", "targetGpu": "Biren_166m", "taskId": "5320487", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23253718728, "estimatedRequiredGiB": 26.013, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 23275790433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779305408, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23275790433}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.058757+00:00", "targetGpu": "Biren_166m", "taskId": "5320489", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952991+00:00", "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23253718728, "estimatedRequiredGiB": 26.013, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 23275790433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779305408, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23275790433}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.058757+00:00", "targetGpu": "Biren_166m", "taskId": "5320489", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "FINAL-Bench/Darwin-27B-RSI", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 53792110192, "estimatedRequiredGiB": 60.14, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 53812206708, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26895998464, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:darwin", "custom_tag:darwin-rsi", "custom_tag:recursive-self-improvement", "custom_tag:model-level-rsi", "custom_tag:rsi", "custom_tag:self-improvement", "custom_tag:self-improving-ai", "custom_tag:self-evolving", "custom_tag:no-human-labels", "custom_tag:label-free", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:chain-of-thought", "custom_tag:gpqa", "custom_tag:supergpqa", "custom_tag:decision-index", "custom_tag:typed-decisions", "custom_tag:jev", "custom_tag:system-2", "custom_tag:qwen3.5", "custom_tag:27b", "custom_tag:vidraft", "custom_tag:final-bench"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 53812206708}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.066396+00:00", "targetGpu": "Biren_166m", "taskId": "5320486", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952552+00:00", "modelId": "FINAL-Bench/Darwin-27B-RSI", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 53792110192, "estimatedRequiredGiB": 60.14, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 53812206708, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26895998464, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:darwin", "custom_tag:darwin-rsi", "custom_tag:recursive-self-improvement", "custom_tag:model-level-rsi", "custom_tag:rsi", "custom_tag:self-improvement", "custom_tag:self-improving-ai", "custom_tag:self-evolving", "custom_tag:no-human-labels", "custom_tag:label-free", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:chain-of-thought", "custom_tag:gpqa", "custom_tag:supergpqa", "custom_tag:decision-index", "custom_tag:typed-decisions", "custom_tag:jev", "custom_tag:system-2", "custom_tag:qwen3.5", "custom_tag:27b", "custom_tag:vidraft", "custom_tag:final-bench"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 53812206708}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.066396+00:00", "targetGpu": "Biren_166m", "taskId": "5320486", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2856860040, "estimatedRequiredGiB": 3.21, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2872281308, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2872281308}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.158731+00:00", "targetGpu": "Biren_166m", "taskId": "5320491", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952878+00:00", "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2856860040, "estimatedRequiredGiB": 3.21, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2872281308, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2872281308}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.158731+00:00", "targetGpu": "Biren_166m", "taskId": "5320491", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6343991648, "estimatedRequiredGiB": 7.115, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6366013051, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1716764160, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6366013051}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.249971+00:00", "targetGpu": "Biren_166m", "taskId": "5320495", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953105+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6343991648, "estimatedRequiredGiB": 7.115, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6366013051, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1716764160, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6366013051}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.249971+00:00", "targetGpu": "Biren_166m", "taskId": "5320495", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2103475788, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:apple-silicon", "custom_tag:oq", "custom_tag:llama", "custom_tag:minicpm", "custom_tag:imatrix", "custom_tag:long-context", "custom_tag:coding", "custom_tag:sharp-template", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2103475788}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.263818+00:00", "targetGpu": "Biren_166m", "taskId": "5320494", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952100+00:00", "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2103475788, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:apple-silicon", "custom_tag:oq", "custom_tag:llama", "custom_tag:minicpm", "custom_tag:imatrix", "custom_tag:long-context", "custom_tag:coding", "custom_tag:sharp-template", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2103475788}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.263818+00:00", "targetGpu": "Biren_166m", "taskId": "5320494", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "b19172cc089e3ab5863a7f6499e4833c8fad38ee16cd9107fd0b438c645cd77f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.259275+00:00", "targetGpu": "Biren_166m", "taskId": "5320492", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951988+00:00", "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "b19172cc089e3ab5863a7f6499e4833c8fad38ee16cd9107fd0b438c645cd77f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.259275+00:00", "targetGpu": "Biren_166m", "taskId": "5320492", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19395158128, "estimatedRequiredGiB": 21.699, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 19416072650, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4022513664, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:betterwright", "custom_tag:browser-agent", "custom_tag:web-agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:diffusion-language-model", "custom_tag:uno", "custom_tag:k2-horizon", "custom_tag:full-finetune"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19416072650}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.262004+00:00", "targetGpu": "Biren_166m", "taskId": "5320493", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952333+00:00", "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19395158128, "estimatedRequiredGiB": 21.699, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 19416072650, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4022513664, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:betterwright", "custom_tag:browser-agent", "custom_tag:web-agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:diffusion-language-model", "custom_tag:uno", "custom_tag:k2-horizon", "custom_tag:full-finetune"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19416072650}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.262004+00:00", "targetGpu": "Biren_166m", "taskId": "5320493", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": 1556071699, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.367421+00:00", "targetGpu": "Biren_166m", "taskId": "5320496", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952663+00:00", "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": 1556071699, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.367421+00:00", "targetGpu": "Biren_166m", "taskId": "5320496", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-llama-mha-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960168568, "estimatedRequiredGiB": 2.344, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2097293495, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2097293495}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.356916+00:00", "targetGpu": "Biren_166m", "taskId": "5320500", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952987+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960168568, "estimatedRequiredGiB": 2.344, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2097293495, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2097293495}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.356916+00:00", "targetGpu": "Biren_166m", "taskId": "5320500", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20984462832, "estimatedRequiredGiB": 23.486, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21014909211, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5865901936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:qwen3-next", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:mixture-of-experts"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21014909211}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.354924+00:00", "targetGpu": "Biren_166m", "taskId": "5320503", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952439+00:00", "modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20984462832, "estimatedRequiredGiB": 23.486, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21014909211, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5865901936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:qwen3-next", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:mixture-of-experts"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21014909211}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.354924+00:00", "targetGpu": "Biren_166m", "taskId": "5320503", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427432, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412809492, "modelscopeLicense": "other", "modelscopeParams": 209741824, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T03:04:40.754950+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 5412809492}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.363783+00:00", "targetGpu": "Biren_166m", "taskId": "5320498", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952546+00:00", "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427432, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412809492, "modelscopeLicense": "other", "modelscopeParams": 209741824, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T03:04:40.754950+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 5412809492}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.363783+00:00", "targetGpu": "Biren_166m", "taskId": "5320498", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593027563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17593027563}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.359842+00:00", "targetGpu": "Biren_166m", "taskId": "5320497", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952229+00:00", "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593027563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17593027563}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.359842+00:00", "targetGpu": "Biren_166m", "taskId": "5320497", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 8145035684, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1605333250, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8145035684}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.361755+00:00", "targetGpu": "Biren_166m", "taskId": "5320501", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952766+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 8145035684, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1605333250, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8145035684}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.361755+00:00", "targetGpu": "Biren_166m", "taskId": "5320501", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11623702006, "estimatedRequiredGiB": 13.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 11651702017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3982569024, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:openai", "custom_tag:gpt-oss", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11651702017}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.648982+00:00", "targetGpu": "Biren_166m", "taskId": "5320514", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11623702006, "estimatedRequiredGiB": 13.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 11651702017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3982569024, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:openai", "custom_tag:gpt-oss", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11651702017}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.648982+00:00", "targetGpu": "Biren_166m", "taskId": "5320514", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4749242120, "estimatedRequiredGiB": 5.332, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 4771310100, "modelscopeLicense": "apache-2.0", "modelscopeParams": 641597440, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4771310100}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.387686+00:00", "targetGpu": "Biren_166m", "taskId": "5320499", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952871+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4749242120, "estimatedRequiredGiB": 5.332, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 4771310100, "modelscopeLicense": "apache-2.0", "modelscopeParams": 641597440, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4771310100}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.387686+00:00", "targetGpu": "Biren_166m", "taskId": "5320499", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.638, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:thinking", "custom_tag:fable5", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:agentic", "custom_tag:coding", "custom_tag:instruction-following", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5045067151}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.562205+00:00", "targetGpu": "Biren_166m", "taskId": "5320507", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951981+00:00", "modelId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.638, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:thinking", "custom_tag:fable5", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:agentic", "custom_tag:coding", "custom_tag:instruction-following", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5045067151}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.562205+00:00", "targetGpu": "Biren_166m", "taskId": "5320507", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Balance", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29644061610, "estimatedRequiredGiB": 33.16, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 29671037772, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8030801776, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:qwen3-next", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:mixture-of-experts", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29671037772}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.643859+00:00", "targetGpu": "Biren_166m", "taskId": "5320512", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952094+00:00", "modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Balance", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29644061610, "estimatedRequiredGiB": 33.16, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 29671037772, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8030801776, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:qwen3-next", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:mixture-of-experts", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29671037772}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.643859+00:00", "targetGpu": "Biren_166m", "taskId": "5320512", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896236664, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898355154, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898355154}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.559066+00:00", "targetGpu": "Biren_166m", "taskId": "5320505", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953099+00:00", "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896236664, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898355154, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898355154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.559066+00:00", "targetGpu": "Biren_166m", "taskId": "5320505", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "danish-foundation-models/DFM-Mimir-v1.5", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3573566200, "estimatedRequiredGiB": 4.03, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 3606214195, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1786775040, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:danish", "custom_tag:english", "custom_tag:hrm-text", "custom_tag:instruction-tuned", "custom_tag:prefix-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3606214195}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.575480+00:00", "targetGpu": "Biren_166m", "taskId": "5320506", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951869+00:00", "modelId": "danish-foundation-models/DFM-Mimir-v1.5", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3573566200, "estimatedRequiredGiB": 4.03, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 3606214195, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1786775040, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:danish", "custom_tag:english", "custom_tag:hrm-text", "custom_tag:instruction-tuned", "custom_tag:prefix-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3606214195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.575480+00:00", "targetGpu": "Biren_166m", "taskId": "5320506", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11771374457, "estimatedRequiredGiB": 13.184, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11796740983, "modelscopeLicense": "other", "modelscopeParams": 301338560, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:3-bit", "custom_tag:affine", "custom_tag:text-only", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 11796740983}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.573876+00:00", "targetGpu": "Biren_166m", "taskId": "5320504", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952328+00:00", "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11771374457, "estimatedRequiredGiB": 13.184, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11796740983, "modelscopeLicense": "other", "modelscopeParams": 301338560, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:3-bit", "custom_tag:affine", "custom_tag:text-only", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 11796740983}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.573876+00:00", "targetGpu": "Biren_166m", "taskId": "5320504", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20473981021, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 20473981021}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.650807+00:00", "targetGpu": "Biren_166m", "taskId": "5320513", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952981+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20473981021, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 20473981021}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.650807+00:00", "targetGpu": "Biren_166m", "taskId": "5320513", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "primitive-ai/Kolibri-1-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Kolibri1ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 45807306768, "estimatedRequiredGiB": 51.228, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kolibri1", "modelscopeFileSize": 45837930112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 44223812896, "modelscopeTags": ["license:apache-2.0", "model_type:kolibri1", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:kolibri", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 45837930112}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.660536+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320511", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952657+00:00", "modelId": "primitive-ai/Kolibri-1-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Kolibri1ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 45807306768, "estimatedRequiredGiB": 51.228, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kolibri1", "modelscopeFileSize": 45837930112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 44223812896, "modelscopeTags": ["license:apache-2.0", "model_type:kolibri1", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:kolibri", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 45837930112}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.660536+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320511", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "primitive-ai/Kolibri-1-NVFP4", "modelProfile": {"architectures": ["Kolibri1ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 47707345296, "estimatedRequiredGiB": 53.351, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kolibri1", "modelscopeFileSize": 47737939154, "modelscopeLicense": "apache-2.0", "modelscopeParams": 42896496000, "modelscopeTags": ["license:apache-2.0", "model_type:kolibri1", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:kolibri", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 47737939154}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.654477+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320508", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952222+00:00", "modelId": "primitive-ai/Kolibri-1-NVFP4", "modelProfile": {"architectures": ["Kolibri1ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 47707345296, "estimatedRequiredGiB": 53.351, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kolibri1", "modelscopeFileSize": 47737939154, "modelscopeLicense": "apache-2.0", "modelscopeParams": 42896496000, "modelscopeTags": ["license:apache-2.0", "model_type:kolibri1", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:kolibri", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 47737939154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.654477+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320508", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "03db37da84f8ca79b8ab2a771eab38713ae74b1a74b47d7451ab360bbdb99462", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.659018+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320509", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952539+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "03db37da84f8ca79b8ab2a771eab38713ae74b1a74b47d7451ab360bbdb99462", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.659018+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320509", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "XingChen-AGI/Xing4.0-29B-A4B-FP8", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33165728400, "estimatedRequiredGiB": 37.07, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 33169537087, "modelscopeLicense": null, "modelscopeParams": 31215031088, "modelscopeTags": ["model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 33169537087}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.656502+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320510", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952762+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B-FP8", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33165728400, "estimatedRequiredGiB": 37.07, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 33169537087, "modelscopeLicense": null, "modelscopeParams": 31215031088, "modelscopeTags": ["model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 33169537087}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.656502+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320510", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19282103457, "estimatedRequiredGiB": 21.582, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19310950017, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:5-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19310950017}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.761540+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320515", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952866+00:00", "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19282103457, "estimatedRequiredGiB": 21.582, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19310950017, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:5-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19310950017}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.761540+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320515", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20593110848, "estimatedRequiredGiB": 23.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20616225866, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:sglang", "custom_tag:gptq", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:safetensors", "custom_tag:qwen3.8", "custom_tag:conversational", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:roleplay", "custom_tag:character", "custom_tag:humanlike", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20616225866}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.866391+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320518", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953094+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20593110848, "estimatedRequiredGiB": 23.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20616225866, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:sglang", "custom_tag:gptq", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:safetensors", "custom_tag:qwen3.8", "custom_tag:conversational", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:roleplay", "custom_tag:character", "custom_tag:humanlike", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20616225866}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.866391+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320518", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19329296879}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.872487+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320519", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951864+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19329296879}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.872487+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320519", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.870624+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320516", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952323+00:00", "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.870624+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320516", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35196531592, "estimatedRequiredGiB": 39.403, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 1411666624, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:text-generation-inference", "custom_tag:qwen3_5", "custom_tag:mlx-vlm", "custom_tag:prompt-rewriter", "custom_tag:prompt enhancer", "custom_tag:apple-silicon", "custom_tag:4-bit", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35256868927}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.868041+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320517", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951976+00:00", "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35196531592, "estimatedRequiredGiB": 39.403, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 1411666624, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:text-generation-inference", "custom_tag:qwen3_5", "custom_tag:mlx-vlm", "custom_tag:prompt-rewriter", "custom_tag:prompt enhancer", "custom_tag:apple-silicon", "custom_tag:4-bit", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35256868927}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.868041+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320517", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171252206, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:ms-swift", "custom_tag:LoRA"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2171252206}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.962831+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320524", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952216+00:00", "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171252206, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:ms-swift", "custom_tag:LoRA"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2171252206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.962831+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320524", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "PleIAs/Baguettotron-MoE", "modelProfile": {"architectures": ["BaguettotronMoeForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26581256560, "estimatedRequiredGiB": 29.713, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "baguettotron_moe", "modelscopeFileSize": 26586426092, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:baguettotron_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:moe", "custom_tag:mixtral", "custom_tag:reasoning", "custom_tag:synthetic-data", "custom_tag:custom_code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26586426092}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.973292+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320523", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952532+00:00", "modelId": "PleIAs/Baguettotron-MoE", "modelProfile": {"architectures": ["BaguettotronMoeForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26581256560, "estimatedRequiredGiB": 29.713, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "baguettotron_moe", "modelscopeFileSize": 26586426092, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:baguettotron_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:moe", "custom_tag:mixtral", "custom_tag:reasoning", "custom_tag:synthetic-data", "custom_tag:custom_code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26586426092}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.973292+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320523", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1216600244, "estimatedRequiredGiB": 1.365, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1221756819, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1221756819}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.955742+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320522", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952089+00:00", "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1216600244, "estimatedRequiredGiB": 1.365, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1221756819, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1221756819}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.955742+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320522", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:23.045201+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320526", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952652+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:23.045201+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320526", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "mlx-community/Mistral-Small-4-119B-2603-OptiQ-2bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 45795315925, "estimatedRequiredGiB": 51.2, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 45812947877, "modelscopeLicense": "apache-2.0", "modelscopeParams": 13531266048, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 45812947877}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.964540+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320521", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952757+00:00", "modelId": "mlx-community/Mistral-Small-4-119B-2603-OptiQ-2bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 45795315925, "estimatedRequiredGiB": 51.2, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 45812947877, "modelscopeLicense": "apache-2.0", "modelscopeParams": 13531266048, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 45812947877}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.964540+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320521", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "IFM/K2-Horizon-MoVA-36B-A4B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 48357709120, "estimatedRequiredGiB": 54.081, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 48390780196, "modelscopeLicense": "apache-2.0", "modelscopeParams": 37444792020, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:36b", "custom_tag:mova", "custom_tag:moe", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 48390780196}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.957174+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320525", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952433+00:00", "modelId": "IFM/K2-Horizon-MoVA-36B-A4B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 48357709120, "estimatedRequiredGiB": 54.081, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 48390780196, "modelscopeLicense": "apache-2.0", "modelscopeParams": 37444792020, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:36b", "custom_tag:mova", "custom_tag:moe", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 48390780196}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.957174+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320525", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:22.961105+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320520", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952976+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.961105+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320520", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:23.062502+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320529", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953089+00:00", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:23.062502+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320529", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30350903424, "estimatedRequiredGiB": 33.932, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": 30361724387, "modelscopeLicense": "other", "modelscopeParams": 5134171936, "modelscopeTags": ["license:other", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30361724387}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:23.066051+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320527", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.951971+00:00", "modelId": "amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30350903424, "estimatedRequiredGiB": 33.932, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": 30361724387, "modelscopeLicense": "other", "modelscopeParams": 5134171936, "modelscopeTags": ["license:other", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30361724387}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:23.066051+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320527", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "juspay/Xor-26B-A4B-NVFP4", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18788485588, "estimatedRequiredGiB": 21.039, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 18825737204, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14386943566, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 18825737204}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:15:23.057114+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5320528", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952862+00:00", "modelId": "juspay/Xor-26B-A4B-NVFP4", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18788485588, "estimatedRequiredGiB": 21.039, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 18825737204, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14386943566, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 18825737204}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:23.057114+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5320528", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6358779576, "estimatedRequiredGiB": 27.418, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 24533499859, "modelscopeLicense": "gpl-2.0", "modelscopeParams": 3043786240, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24533499859}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:34:33.244601+00:00", "targetGpu": "Biren_166m", "taskId": "5320842", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952855+00:00", "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6358779576, "estimatedRequiredGiB": 27.418, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 24533499859, "modelscopeLicense": "gpl-2.0", "modelscopeParams": 3043786240, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24533499859}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.244601+00:00", "targetGpu": "Biren_166m", "taskId": "5320842", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "webAI-Official/TwIL-LM3-Pro", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517272, "estimatedRequiredGiB": 29.512, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 26407018955, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26407018955}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:34:33.177398+00:00", "targetGpu": "Biren_166m", "taskId": "5320841", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952647+00:00", "modelId": "webAI-Official/TwIL-LM3-Pro", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517272, "estimatedRequiredGiB": 29.512, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 26407018955, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26407018955}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.177398+00:00", "targetGpu": "Biren_166m", "taskId": "5320841", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "webAI-Official/TwIL-LM2", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5067121544, "estimatedRequiredGiB": 20.413, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 18264867356, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:twil-lm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18264867356}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:34:33.170764+00:00", "targetGpu": "Biren_166m", "taskId": "5320839", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952210+00:00", "modelId": "webAI-Official/TwIL-LM2", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5067121544, "estimatedRequiredGiB": 20.413, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 18264867356, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:twil-lm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18264867356}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.170764+00:00", "targetGpu": "Biren_166m", "taskId": "5320839", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/Hemmingway-1-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18966599842, "estimatedRequiredGiB": 21.22, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18986905904, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:writing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18986905904}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:34:33.175204+00:00", "targetGpu": "Biren_166m", "taskId": "5320848", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952526+00:00", "modelId": "mlx-community/Hemmingway-1-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18966599842, "estimatedRequiredGiB": 21.22, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18986905904, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:writing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18986905904}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.175204+00:00", "targetGpu": "Biren_166m", "taskId": "5320848", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1987222504, "estimatedRequiredGiB": 2.406, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2152567281, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2152567281}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:34:33.247174+00:00", "targetGpu": "Biren_166m", "taskId": "5320843", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951965+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1987222504, "estimatedRequiredGiB": 2.406, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2152567281, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2152567281}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.247174+00:00", "targetGpu": "Biren_166m", "taskId": "5320843", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2010737208, "estimatedRequiredGiB": 2.432, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2176034009, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2176034009}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:34:33.167694+00:00", "targetGpu": "Biren_166m", "taskId": "5320845", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952427+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2010737208, "estimatedRequiredGiB": 2.432, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2176034009, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2176034009}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.167694+00:00", "targetGpu": "Biren_166m", "taskId": "5320845", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15859925253, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15859925253}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:34:33.155386+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320840", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952318+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15859925253, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15859925253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.155386+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320840", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242696, "estimatedRequiredGiB": 2.46, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2201523288, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2201523288}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:34:33.246121+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320837", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953072+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242696, "estimatedRequiredGiB": 2.46, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2201523288, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2201523288}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.246121+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320837", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033920112, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199304207, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199304207}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:34:33.169263+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320838", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952971+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033920112, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199304207, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199304207}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.169263+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320838", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": 36069420, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:34:33.164156+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320847", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952084+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": 36069420, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.164156+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320847", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7120897697, "modelscopeLicense": "mit", "modelscopeParams": 1915564544, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:mimo_v2", "custom_tag:agentic", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7120897697}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:34:33.158538+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320844", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951857+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7120897697, "modelscopeLicense": "mit", "modelscopeParams": 1915564544, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:mimo_v2", "custom_tag:agentic", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7120897697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.158538+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320844", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1932905544, "estimatedRequiredGiB": 2.313, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2070028245, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2070028245}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:34:33.173573+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320846", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952751+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1932905544, "estimatedRequiredGiB": 2.313, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2070028245, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2070028245}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:34:33.173573+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320846", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.269594+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320851", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952966+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.269594+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320851", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033754200, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199119539, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199119539}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.258284+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320850", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952312+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033754200, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199119539, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199119539}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.258284+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320850", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1933022288, "estimatedRequiredGiB": 2.322, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2077758206, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2077758206}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.263007+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320852", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952077+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1933022288, "estimatedRequiredGiB": 2.322, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2077758206, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2077758206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.263007+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320852", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-llama-mha-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960285320, "estimatedRequiredGiB": 2.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2105033791, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2105033791}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.260498+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320849", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951850+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960285320, "estimatedRequiredGiB": 2.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2105033791, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2105033791}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.260498+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320849", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.328612+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320853", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952520+00:00", "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.328612+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320853", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3662928280, "estimatedRequiredGiB": 4.11, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3677830216, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq", "custom_tag:preview"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3677830216}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.264608+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320855", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952422+00:00", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3662928280, "estimatedRequiredGiB": 4.11, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3677830216, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq", "custom_tag:preview"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3677830216}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.264608+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320855", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 467369015}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.272338+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320856", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952203+00:00", "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 467369015}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.272338+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320856", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.61, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19336478290, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19336478290}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.273637+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320854", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952746+00:00", "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.61, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19336478290, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19336478290}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.273637+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320854", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.363114+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320859", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953067+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.363114+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320859", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "togethercomputer/Tev1-4B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342812725, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342812725}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.374943+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320857", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951958+00:00", "modelId": "togethercomputer/Tev1-4B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342812725, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342812725}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.374943+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320857", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "togethercomputer/Tev1-0.8B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1746942600, "estimatedRequiredGiB": 1.978, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 1769900320, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1769900320}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.361277+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320858", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952849+00:00", "modelId": "togethercomputer/Tev1-0.8B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1746942600, "estimatedRequiredGiB": 1.978, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 1769900320, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1769900320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.361277+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320858", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.359681+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320860", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952640+00:00", "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.359681+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320860", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199612614, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199612614}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.463228+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320862", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952307+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199612614, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199612614}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.463228+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320862", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-attnres-block1-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199622478, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199622478}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.477950+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320861", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951842+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block1-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199622478, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199622478}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.477950+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320861", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 1784320455, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.554451+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320867", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952072+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 1784320455, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.554451+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320867", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.754698+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320874", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953062+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.754698+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320874", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.563131+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320870", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952197+00:00", "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.563131+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320870", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "burtenshaw/nanochat", "modelProfile": {"architectures": ["NanoChatForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8583142248, "estimatedRequiredGiB": 9.603, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanochat", "modelscopeFileSize": 8592610065, "modelscopeLicense": "mit", "modelscopeParams": 161546240, "modelscopeTags": ["license:mit", "model_type:nanochat", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8592610065}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.561419+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320866", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952962+00:00", "modelId": "burtenshaw/nanochat", "modelProfile": {"architectures": ["NanoChatForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8583142248, "estimatedRequiredGiB": 9.603, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanochat", "modelscopeFileSize": 8592610065, "modelscopeLicense": "mit", "modelscopeParams": 161546240, "modelscopeTags": ["license:mit", "model_type:nanochat", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8592610065}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.561419+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320866", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033585336, "estimatedRequiredGiB": 2.457, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2198654500, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2198654500}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.575722+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320869", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952635+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033585336, "estimatedRequiredGiB": 2.457, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2198654500, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2198654500}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.575722+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320869", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871536, "estimatedRequiredGiB": 2.418, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2163952661, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2163952661}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.559645+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320863", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952416+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871536, "estimatedRequiredGiB": 2.418, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2163952661, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2163952661}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.559645+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320863", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23253718728, "estimatedRequiredGiB": 26.013, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 23275790433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779305408, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23275790433}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.574208+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320865", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952515+00:00", "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23253718728, "estimatedRequiredGiB": 26.013, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 23275790433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779305408, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23275790433}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.574208+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320865", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "FINAL-Bench/Darwin-27B-RSI", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 53792110192, "estimatedRequiredGiB": 60.14, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 53812206708, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26895998464, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:darwin", "custom_tag:darwin-rsi", "custom_tag:recursive-self-improvement", "custom_tag:model-level-rsi", "custom_tag:rsi", "custom_tag:self-improvement", "custom_tag:self-improving-ai", "custom_tag:self-evolving", "custom_tag:no-human-labels", "custom_tag:label-free", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:chain-of-thought", "custom_tag:gpqa", "custom_tag:supergpqa", "custom_tag:decision-index", "custom_tag:typed-decisions", "custom_tag:jev", "custom_tag:system-2", "custom_tag:qwen3.5", "custom_tag:27b", "custom_tag:vidraft", "custom_tag:final-bench"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 53812206708}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.573022+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320864", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952741+00:00", "modelId": "FINAL-Bench/Darwin-27B-RSI", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 53792110192, "estimatedRequiredGiB": 60.14, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 53812206708, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26895998464, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:darwin", "custom_tag:darwin-rsi", "custom_tag:recursive-self-improvement", "custom_tag:model-level-rsi", "custom_tag:rsi", "custom_tag:self-improvement", "custom_tag:self-improving-ai", "custom_tag:self-evolving", "custom_tag:no-human-labels", "custom_tag:label-free", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:chain-of-thought", "custom_tag:gpqa", "custom_tag:supergpqa", "custom_tag:decision-index", "custom_tag:typed-decisions", "custom_tag:jev", "custom_tag:system-2", "custom_tag:qwen3.5", "custom_tag:27b", "custom_tag:vidraft", "custom_tag:final-bench"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 53812206708}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.573022+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320864", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2856860040, "estimatedRequiredGiB": 3.21, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2872281308, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2872281308}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.771681+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320872", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952302+00:00", "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2856860040, "estimatedRequiredGiB": 3.21, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2872281308, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2872281308}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.771681+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320872", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6343991648, "estimatedRequiredGiB": 7.115, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6366013051, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1716764160, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6366013051}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.749110+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320868", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952845+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6343991648, "estimatedRequiredGiB": 7.115, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6366013051, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1716764160, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6366013051}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.749110+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320868", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2103475788, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:apple-silicon", "custom_tag:oq", "custom_tag:llama", "custom_tag:minicpm", "custom_tag:imatrix", "custom_tag:long-context", "custom_tag:coding", "custom_tag:sharp-template", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2103475788}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.949561+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320876", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952957+00:00", "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2103475788, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:apple-silicon", "custom_tag:oq", "custom_tag:llama", "custom_tag:minicpm", "custom_tag:imatrix", "custom_tag:long-context", "custom_tag:coding", "custom_tag:sharp-template", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2103475788}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.949561+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320876", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "82efa29257bb1050c4e14463aa1ab12c15080adaf15fd3aeeb70915db5840bff", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.944870+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320875", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952066+00:00", "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "82efa29257bb1050c4e14463aa1ab12c15080adaf15fd3aeeb70915db5840bff", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.944870+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320875", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19395158128, "estimatedRequiredGiB": 21.699, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 19416072650, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4022513664, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:betterwright", "custom_tag:browser-agent", "custom_tag:web-agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:diffusion-language-model", "custom_tag:uno", "custom_tag:k2-horizon", "custom_tag:full-finetune"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19416072650}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.762283+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320871", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951952+00:00", "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19395158128, "estimatedRequiredGiB": 21.699, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 19416072650, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4022513664, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:betterwright", "custom_tag:browser-agent", "custom_tag:web-agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:diffusion-language-model", "custom_tag:uno", "custom_tag:k2-horizon", "custom_tag:full-finetune"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19416072650}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.762283+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320871", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": 1556071699, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.948371+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320877", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952411+00:00", "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": 1556071699, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.948371+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320877", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-llama-mha-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960168568, "estimatedRequiredGiB": 2.344, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2097293495, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2097293495}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:45.851166+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320873", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951833+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960168568, "estimatedRequiredGiB": 2.344, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2097293495, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2097293495}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:45.851166+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320873", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427432, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412809492, "modelscopeLicense": "other", "modelscopeParams": 209741824, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412809492}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:46.144427+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320878", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952190+00:00", "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427432, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412809492, "modelscopeLicense": "other", "modelscopeParams": 209741824, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412809492}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.144427+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320878", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593027563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17593027563}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:46.166675+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320882", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952510+00:00", "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593027563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17593027563}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.166675+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320882", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 8145035684, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1605333250, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8145035684}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:46.165208+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320880", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952736+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 8145035684, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1605333250, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8145035684}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.165208+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320880", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11623702006, "estimatedRequiredGiB": 13.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 11651702017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3982569024, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:openai", "custom_tag:gpt-oss", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11651702017}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:46.170338+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320879", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952839+00:00", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11623702006, "estimatedRequiredGiB": 13.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 11651702017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3982569024, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:openai", "custom_tag:gpt-oss", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11651702017}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.170338+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320879", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4749242120, "estimatedRequiredGiB": 5.332, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 4771310100, "modelscopeLicense": "apache-2.0", "modelscopeParams": 641597440, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4771310100}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:46.168164+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320881", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952629+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4749242120, "estimatedRequiredGiB": 5.332, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 4771310100, "modelscopeLicense": "apache-2.0", "modelscopeParams": 641597440, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4771310100}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.168164+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320881", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.638, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:thinking", "custom_tag:fable5", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:agentic", "custom_tag:coding", "custom_tag:instruction-following", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5045067151}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:46.253231+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320883", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953057+00:00", "modelId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.638, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:thinking", "custom_tag:fable5", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:agentic", "custom_tag:coding", "custom_tag:instruction-following", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5045067151}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.253231+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320883", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896236664, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898355154, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898355154}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:46.272792+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320884", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951946+00:00", "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896236664, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898355154, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898355154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.272792+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320884", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "danish-foundation-models/DFM-Mimir-v1.5", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3573566200, "estimatedRequiredGiB": 4.03, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 3606214195, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1786775040, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:danish", "custom_tag:english", "custom_tag:hrm-text", "custom_tag:instruction-tuned", "custom_tag:prefix-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3606214195}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:46.275101+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320885", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952296+00:00", "modelId": "danish-foundation-models/DFM-Mimir-v1.5", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3573566200, "estimatedRequiredGiB": 4.03, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 3606214195, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1786775040, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:danish", "custom_tag:english", "custom_tag:hrm-text", "custom_tag:instruction-tuned", "custom_tag:prefix-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3606214195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.275101+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320885", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11771374457, "estimatedRequiredGiB": 13.184, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11796740983, "modelscopeLicense": "other", "modelscopeParams": 301338560, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:3-bit", "custom_tag:affine", "custom_tag:text-only", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11796740983}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:46.359396+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320892", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952061+00:00", "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11771374457, "estimatedRequiredGiB": 13.184, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11796740983, "modelscopeLicense": "other", "modelscopeParams": 301338560, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:3-bit", "custom_tag:affine", "custom_tag:text-only", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11796740983}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.359396+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320892", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20473981021, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20473981021}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:46.356016+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320886", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951827+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20473981021, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20473981021}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.356016+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320886", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "1808282a6a7e87463f4fe68a059e74642ad7fba49ec04a246f0c3ea29ccfa12b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:46.372146+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320887", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952174+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "1808282a6a7e87463f4fe68a059e74642ad7fba49ec04a246f0c3ea29ccfa12b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.372146+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320887", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "XingChen-AGI/Xing4.0-29B-A4B-FP8", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33165728400, "estimatedRequiredGiB": 37.07, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 33169537087, "modelscopeLicense": null, "modelscopeParams": 31215031088, "modelscopeTags": ["model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 33169537087}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:46.367923+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320889", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952952+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B-FP8", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33165728400, "estimatedRequiredGiB": 37.07, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 33169537087, "modelscopeLicense": null, "modelscopeParams": 31215031088, "modelscopeTags": ["model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 33169537087}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.367923+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320889", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:46.366014+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320893", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952405+00:00", "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.366014+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320893", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171252206, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:ms-swift", "custom_tag:LoRA"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2171252206}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:46.378032+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320891", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952505+00:00", "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171252206, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:ms-swift", "custom_tag:LoRA"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2171252206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.378032+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320891", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "PleIAs/Baguettotron-MoE", "modelProfile": {"architectures": ["BaguettotronMoeForCausalLM"], "configFingerprint": "58bd440e460cf3e4d9271b3c32c451e80254e59faf47ce55dcda11588cf4117e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26581256560, "estimatedRequiredGiB": 29.713, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "baguettotron_moe", "modelscopeFileSize": 26586426092, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:baguettotron_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:moe", "custom_tag:mixtral", "custom_tag:reasoning", "custom_tag:synthetic-data", "custom_tag:custom_code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26586426092}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:46.374657+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320888", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952730+00:00", "modelId": "PleIAs/Baguettotron-MoE", "modelProfile": {"architectures": ["BaguettotronMoeForCausalLM"], "configFingerprint": "58bd440e460cf3e4d9271b3c32c451e80254e59faf47ce55dcda11588cf4117e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26581256560, "estimatedRequiredGiB": 29.713, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "baguettotron_moe", "modelscopeFileSize": 26586426092, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:baguettotron_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:moe", "custom_tag:mixtral", "custom_tag:reasoning", "custom_tag:synthetic-data", "custom_tag:custom_code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26586426092}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.374657+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320888", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "58bd440e460cf3e4d9271b3c32c451e80254e59faf47ce55dcda11588cf4117e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1216600244, "estimatedRequiredGiB": 1.365, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1221756819, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1221756819}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:46.380008+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320890", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952623+00:00", "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "58bd440e460cf3e4d9271b3c32c451e80254e59faf47ce55dcda11588cf4117e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1216600244, "estimatedRequiredGiB": 1.365, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1221756819, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1221756819}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.380008+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320890", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:46.458983+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320894", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.953053+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.458983+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320894", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:35:46.457520+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320895", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952834+00:00", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:35:46.457520+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320895", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "263f4cb5e779de4b0b61f97834829c54e77136bc79bad2edf386dfd62b327794", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:46:35.647771+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321044", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952500+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "263f4cb5e779de4b0b61f97834829c54e77136bc79bad2edf386dfd62b327794", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:46:35.647771+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321044", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242696, "estimatedRequiredGiB": 2.46, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2201523288, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2201523288}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:46:35.568027+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321039", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952054+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242696, "estimatedRequiredGiB": 2.46, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2201523288, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2201523288}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:46:35.568027+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321039", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033920112, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199304207, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199304207}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:46:35.571842+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321045", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952947+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033920112, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199304207, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199304207}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:46:35.571842+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321045", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": 36069420, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:46:35.565915+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321046", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.951819+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": 36069420, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:46:35.565915+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321046", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1932905544, "estimatedRequiredGiB": 2.313, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2070028245, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2070028245}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:46:35.651628+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321042", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952828+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1932905544, "estimatedRequiredGiB": 2.313, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2070028245, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2070028245}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:46:35.651628+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321042", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:46:35.570093+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321041", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952399+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:46:35.570093+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321041", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033754200, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199119539, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199119539}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:46:35.575997+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321047", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952725+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033754200, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199119539, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199119539}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:46:35.575997+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321047", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1933022288, "estimatedRequiredGiB": 2.322, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2077758206, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2077758206}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:46:35.650385+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321048", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952616+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1933022288, "estimatedRequiredGiB": 2.322, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2077758206, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2077758206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:46:35.650385+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321048", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-llama-mha-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960285320, "estimatedRequiredGiB": 2.353, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2105033791, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2105033791}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:46:35.573750+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321050", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952168+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960285320, "estimatedRequiredGiB": 2.353, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2105033791, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2105033791}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:46:35.573750+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321050", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:46:35.654004+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321038", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.953048+00:00", "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:46:35.654004+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321038", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19282103457, "estimatedRequiredGiB": 21.582, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19310950017, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:5-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19310950017}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:46:35.561317+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321043", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.951939+00:00", "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19282103457, "estimatedRequiredGiB": 21.582, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19310950017, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:5-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19310950017}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:46:35.561317+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321043", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20321390048, "estimatedRequiredGiB": 22.734, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20341996128, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20341996128}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:46:35.564547+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321040", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952291+00:00", "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20321390048, "estimatedRequiredGiB": 22.734, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20341996128, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20341996128}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:46:35.564547+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321040", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20593110848, "estimatedRequiredGiB": 23.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20616225866, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:sglang", "custom_tag:gptq", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:safetensors", "custom_tag:qwen3.8", "custom_tag:conversational", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:roleplay", "custom_tag:character", "custom_tag:humanlike", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20616225866}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:41.568827+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321049", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.951933+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20593110848, "estimatedRequiredGiB": 23.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20616225866, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:sglang", "custom_tag:gptq", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:safetensors", "custom_tag:qwen3.8", "custom_tag:conversational", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:roleplay", "custom_tag:character", "custom_tag:humanlike", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20616225866}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.568827+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321049", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3662928280, "estimatedRequiredGiB": 4.11, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3677830216, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq", "custom_tag:preview"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3677830216}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:41.864846+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321057", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952494+00:00", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3662928280, "estimatedRequiredGiB": 4.11, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3677830216, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq", "custom_tag:preview"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3677830216}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.864846+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321057", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 467369015}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:41.656436+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321055", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.951812+00:00", "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 467369015}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.656436+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321055", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:41.971389+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321062", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952280+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.971389+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321062", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:41.660362+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321054", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952049+00:00", "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.660362+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321054", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "785069d14d27b828ee50a34932a2fa1917fd842d075189f20fc7defd52ef2db4", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:41.964098+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321059", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.953043+00:00", "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "785069d14d27b828ee50a34932a2fa1917fd842d075189f20fc7defd52ef2db4", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.964098+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321059", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199612614, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199612614}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:41.653611+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321051", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952285+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199612614, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199612614}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.653611+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321051", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-attnres-block1-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199622478, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199622478}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:41.757839+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321053", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952161+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block1-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199622478, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199622478}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.757839+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321053", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 1784320455, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:41.756287+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321052", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952941+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 1784320455, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.756287+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321052", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "OsaurusAI/Raptor-0.6-4B-JANG_4M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2635323720, "estimatedRequiredGiB": 2.962, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2650224659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2650224659}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:41.751476+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321056", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952394+00:00", "modelId": "OsaurusAI/Raptor-0.6-4B-JANG_4M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2635323720, "estimatedRequiredGiB": 2.962, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2650224659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2650224659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.751476+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321056", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:41.967785+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321060", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.951927+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.967785+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321060", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:41.958543+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321063", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952823+00:00", "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.958543+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321063", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "burtenshaw/nanochat", "modelProfile": {"architectures": ["NanoChatForCausalLM"], "configFingerprint": "785069d14d27b828ee50a34932a2fa1917fd842d075189f20fc7defd52ef2db4", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8583142248, "estimatedRequiredGiB": 9.603, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanochat", "modelscopeFileSize": 8592610065, "modelscopeLicense": "mit", "modelscopeParams": 161546240, "modelscopeTags": ["license:mit", "model_type:nanochat", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8592610065}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:41.855732+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321058", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952720+00:00", "modelId": "burtenshaw/nanochat", "modelProfile": {"architectures": ["NanoChatForCausalLM"], "configFingerprint": "785069d14d27b828ee50a34932a2fa1917fd842d075189f20fc7defd52ef2db4", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8583142248, "estimatedRequiredGiB": 9.603, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanochat", "modelscopeFileSize": 8592610065, "modelscopeLicense": "mit", "modelscopeParams": 161546240, "modelscopeTags": ["license:mit", "model_type:nanochat", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8592610065}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.855732+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321058", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171252206, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:ms-swift", "custom_tag:LoRA"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2171252206}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.075531+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321064", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952389+00:00", "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171252206, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:ms-swift", "custom_tag:LoRA"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2171252206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.075531+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321064", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033585336, "estimatedRequiredGiB": 2.457, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2198654500, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2198654500}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.073173+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321066", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952044+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033585336, "estimatedRequiredGiB": 2.457, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2198654500, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2198654500}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.073173+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321066", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871536, "estimatedRequiredGiB": 2.418, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2163952661, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2163952661}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:41.955032+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321061", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952610+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871536, "estimatedRequiredGiB": 2.418, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2163952661, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2163952661}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:41.955032+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321061", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23253718728, "estimatedRequiredGiB": 26.013, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 23275790433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779305408, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23275790433}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.150650+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321070", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952714+00:00", "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23253718728, "estimatedRequiredGiB": 26.013, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 23275790433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779305408, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23275790433}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.150650+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321070", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2856860040, "estimatedRequiredGiB": 3.21, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2872281308, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2872281308}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.147712+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321065", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952936+00:00", "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2856860040, "estimatedRequiredGiB": 3.21, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2872281308, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2872281308}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.147712+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321065", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6343991648, "estimatedRequiredGiB": 7.115, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6366013051, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1716764160, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6366013051}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.066030+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321067", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.951804+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6343991648, "estimatedRequiredGiB": 7.115, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6366013051, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1716764160, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6366013051}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.066030+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321067", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2103475788, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:apple-silicon", "custom_tag:oq", "custom_tag:llama", "custom_tag:minicpm", "custom_tag:imatrix", "custom_tag:long-context", "custom_tag:coding", "custom_tag:sharp-template", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2103475788}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.149448+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321072", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952155+00:00", "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2103475788, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:apple-silicon", "custom_tag:oq", "custom_tag:llama", "custom_tag:minicpm", "custom_tag:imatrix", "custom_tag:long-context", "custom_tag:coding", "custom_tag:sharp-template", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2103475788}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.149448+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321072", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "391b7c8eba715d1090a3f4b6f9ebce16b19b727a654118d70f53253a3a6efa3b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.155888+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321071", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952605+00:00", "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "391b7c8eba715d1090a3f4b6f9ebce16b19b727a654118d70f53253a3a6efa3b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.155888+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321071", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19395158128, "estimatedRequiredGiB": 21.699, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 19416072650, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4022513664, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:betterwright", "custom_tag:browser-agent", "custom_tag:web-agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:diffusion-language-model", "custom_tag:uno", "custom_tag:k2-horizon", "custom_tag:full-finetune"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19416072650}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.151731+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321068", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952488+00:00", "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19395158128, "estimatedRequiredGiB": 21.699, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 19416072650, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4022513664, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:betterwright", "custom_tag:browser-agent", "custom_tag:web-agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:diffusion-language-model", "custom_tag:uno", "custom_tag:k2-horizon", "custom_tag:full-finetune"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19416072650}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.151731+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321068", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "785069d14d27b828ee50a34932a2fa1917fd842d075189f20fc7defd52ef2db4", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": 1556071699, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.648710+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321081", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952931+00:00", "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "785069d14d27b828ee50a34932a2fa1917fd842d075189f20fc7defd52ef2db4", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": 1556071699, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.648710+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321081", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-llama-mha-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960168568, "estimatedRequiredGiB": 2.344, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2097293495, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2097293495}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.158719+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321073", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952817+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960168568, "estimatedRequiredGiB": 2.344, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2097293495, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2097293495}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.158719+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321073", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "PleIAs/Baguettotron-MoE", "modelProfile": {"architectures": ["BaguettotronMoeForCausalLM"], "configFingerprint": "785069d14d27b828ee50a34932a2fa1917fd842d075189f20fc7defd52ef2db4", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26581256560, "estimatedRequiredGiB": 29.713, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "baguettotron_moe", "modelscopeFileSize": 26586426092, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:baguettotron_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:moe", "custom_tag:mixtral", "custom_tag:reasoning", "custom_tag:synthetic-data", "custom_tag:custom_code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26586426092}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.255754+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321075", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.951920+00:00", "modelId": "PleIAs/Baguettotron-MoE", "modelProfile": {"architectures": ["BaguettotronMoeForCausalLM"], "configFingerprint": "785069d14d27b828ee50a34932a2fa1917fd842d075189f20fc7defd52ef2db4", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26581256560, "estimatedRequiredGiB": 29.713, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "baguettotron_moe", "modelscopeFileSize": 26586426092, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:baguettotron_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:moe", "custom_tag:mixtral", "custom_tag:reasoning", "custom_tag:synthetic-data", "custom_tag:custom_code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26586426092}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.255754+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321075", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "785069d14d27b828ee50a34932a2fa1917fd842d075189f20fc7defd52ef2db4", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1216600244, "estimatedRequiredGiB": 1.365, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1221756819, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1221756819}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.248094+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321076", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.953038+00:00", "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "785069d14d27b828ee50a34932a2fa1917fd842d075189f20fc7defd52ef2db4", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1216600244, "estimatedRequiredGiB": 1.365, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1221756819, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1221756819}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.248094+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321076", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427432, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412809492, "modelscopeLicense": "other", "modelscopeParams": 209741824, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412809492}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.348134+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321069", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952275+00:00", "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427432, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412809492, "modelscopeLicense": "other", "modelscopeParams": 209741824, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412809492}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.348134+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321069", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593027563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17593027563}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.668127+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321082", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952599+00:00", "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593027563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17593027563}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.668127+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321082", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 8145035684, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1605333250, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8145035684}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.349700+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321074", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.951797+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 8145035684, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1605333250, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8145035684}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.349700+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321074", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11623702006, "estimatedRequiredGiB": 13.022, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 11651702017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3982569024, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:openai", "custom_tag:gpt-oss", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11651702017}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.556514+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321077", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952383+00:00", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11623702006, "estimatedRequiredGiB": 13.022, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 11651702017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3982569024, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:openai", "custom_tag:gpt-oss", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11651702017}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.556514+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321077", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4749242120, "estimatedRequiredGiB": 5.332, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 4771310100, "modelscopeLicense": "apache-2.0", "modelscopeParams": 641597440, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4771310100}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.656704+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321078", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952708+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4749242120, "estimatedRequiredGiB": 5.332, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 4771310100, "modelscopeLicense": "apache-2.0", "modelscopeParams": 641597440, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4771310100}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.656704+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321078", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474195, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320426072, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:fp16", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320426072}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.666092+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321083", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952482+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474195, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320426072, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:fp16", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320426072}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.666092+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321083", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.638, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:thinking", "custom_tag:fable5", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:agentic", "custom_tag:coding", "custom_tag:instruction-following", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5045067151}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.671566+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321084", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.953032+00:00", "modelId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.638, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:thinking", "custom_tag:fable5", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:agentic", "custom_tag:coding", "custom_tag:instruction-following", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5045067151}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.671566+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321084", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896236664, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898355154, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898355154}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.654985+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321079", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952150+00:00", "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896236664, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898355154, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898355154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.654985+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321079", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "danish-foundation-models/DFM-Mimir-v1.5", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3573566200, "estimatedRequiredGiB": 4.03, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 3606214195, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1786775040, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:danish", "custom_tag:english", "custom_tag:hrm-text", "custom_tag:instruction-tuned", "custom_tag:prefix-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3606214195}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.669715+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321080", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952812+00:00", "modelId": "danish-foundation-models/DFM-Mimir-v1.5", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3573566200, "estimatedRequiredGiB": 4.03, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 3606214195, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1786775040, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:danish", "custom_tag:english", "custom_tag:hrm-text", "custom_tag:instruction-tuned", "custom_tag:prefix-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3606214195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.669715+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321080", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.752950+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321085", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.951913+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.752950+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321085", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:47:42.948174+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321086", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952269+00:00", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.948174+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321086", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15859925253, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15859925253}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:56:23.868816+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321209", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952372+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15859925253, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15859925253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.868816+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321209", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "497ab91cb1ba127d73c571f3ec8297e040a03e575e3c6ce93ccd36aa425663ac", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:56:23.928461+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321201", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952703+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "497ab91cb1ba127d73c571f3ec8297e040a03e575e3c6ce93ccd36aa425663ac", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.928461+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321201", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242696, "estimatedRequiredGiB": 2.46, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2201523288, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2201523288}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:56:23.932288+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321205", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952592+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242696, "estimatedRequiredGiB": 2.46, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2201523288, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2201523288}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.932288+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321205", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033920112, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199304207, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199304207}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:56:23.938848+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321210", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952031+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033920112, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199304207, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199304207}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.938848+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321210", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": 36069420, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:56:23.951340+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321208", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952378+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": 36069420, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.951340+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321208", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7120897697, "modelscopeLicense": "mit", "modelscopeParams": 1915564544, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:mimo_v2", "custom_tag:agentic", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7120897697}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:56:23.866238+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321206", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952037+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7120897697, "modelscopeLicense": "mit", "modelscopeParams": 1915564544, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:mimo_v2", "custom_tag:agentic", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7120897697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.866238+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321206", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1932905544, "estimatedRequiredGiB": 2.313, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2070028245, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2070028245}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:56:23.936620+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321200", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.951790+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1932905544, "estimatedRequiredGiB": 2.313, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2070028245, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2070028245}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.936620+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321200", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:56:23.930642+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321203", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952477+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.930642+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321203", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033754200, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199119539, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199119539}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:56:23.935477+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321204", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.953027+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033754200, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199119539, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199119539}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.935477+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321204", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1933022288, "estimatedRequiredGiB": 2.322, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2077758206, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2077758206}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:56:23.873128+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321199", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952926+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1933022288, "estimatedRequiredGiB": 2.322, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2077758206, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2077758206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.873128+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321199", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-llama-mha-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960285320, "estimatedRequiredGiB": 2.353, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2105033791, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2105033791}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:56:23.876580+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321207", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952144+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960285320, "estimatedRequiredGiB": 2.353, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2105033791, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2105033791}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.876580+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321207", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19282103457, "estimatedRequiredGiB": 21.582, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19310950017, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:5-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19310950017}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:56:23.934000+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321202", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952807+00:00", "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19282103457, "estimatedRequiredGiB": 21.582, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19310950017, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:5-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19310950017}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.934000+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321202", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20321390048, "estimatedRequiredGiB": 22.734, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20341996128, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20341996128}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:49.756665+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321211", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952921+00:00", "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20321390048, "estimatedRequiredGiB": 22.734, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20341996128, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20341996128}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.756665+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321211", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20593110848, "estimatedRequiredGiB": 23.04, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20616225866, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:sglang", "custom_tag:gptq", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:safetensors", "custom_tag:qwen3.8", "custom_tag:conversational", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:roleplay", "custom_tag:character", "custom_tag:humanlike", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20616225866}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:49.944154+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321215", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.953021+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20593110848, "estimatedRequiredGiB": 23.04, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20616225866, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:sglang", "custom_tag:gptq", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:safetensors", "custom_tag:qwen3.8", "custom_tag:conversational", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:roleplay", "custom_tag:character", "custom_tag:humanlike", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20616225866}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.944154+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321215", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 467369015}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:49.962484+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321218", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.951907+00:00", "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 467369015}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.962484+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321218", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.61, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19336478290, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19336478290}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:49.759129+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321212", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952138+00:00", "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.61, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19336478290, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19336478290}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.759129+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321212", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19329296879}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.069956+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321221", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952915+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19329296879}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.069956+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321221", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:49.850687+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321219", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952698+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.850687+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321219", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "togethercomputer/Tev1-4B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342812725, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342812725}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:49.857043+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321213", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952585+00:00", "modelId": "togethercomputer/Tev1-4B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342812725, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342812725}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.857043+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321213", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "togethercomputer/Tev1-0.8B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1746942600, "estimatedRequiredGiB": 1.978, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 1769900320, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1769900320}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.064744+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321223", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952025+00:00", "modelId": "togethercomputer/Tev1-0.8B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1746942600, "estimatedRequiredGiB": 1.978, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 1769900320, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1769900320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.064744+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321223", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:49.852267+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321216", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952471+00:00", "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.852267+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321216", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.062922+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321220", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.951782+00:00", "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.062922+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321220", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "webAI-Official/TwIL-LM2", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5067121544, "estimatedRequiredGiB": 20.413, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 18264867356, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:twil-lm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18264867356}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:49.859242+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321214", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952801+00:00", "modelId": "webAI-Official/TwIL-LM2", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5067121544, "estimatedRequiredGiB": 20.413, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 18264867356, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:twil-lm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18264867356}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.859242+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321214", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199612614, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199612614}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.067918+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321222", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952366+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199612614, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199612614}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.067918+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321222", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-attnres-block1-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199622478, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199622478}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.148098+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321224", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952132+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block1-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199622478, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199622478}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.148098+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321224", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 1784320455, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:49.964092+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321217", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952263+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 1784320455, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.964092+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321217", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.265569+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321226", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.951899+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.265569+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321226", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.261621+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321229", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.953016+00:00", "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.261621+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321229", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "burtenshaw/nanochat", "modelProfile": {"architectures": ["NanoChatForCausalLM"], "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8583142248, "estimatedRequiredGiB": 9.603, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanochat", "modelscopeFileSize": 8592610065, "modelscopeLicense": "mit", "modelscopeParams": 161546240, "modelscopeTags": ["license:mit", "model_type:nanochat", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8592610065}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.256417+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321230", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952795+00:00", "modelId": "burtenshaw/nanochat", "modelProfile": {"architectures": ["NanoChatForCausalLM"], "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8583142248, "estimatedRequiredGiB": 9.603, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanochat", "modelscopeFileSize": 8592610065, "modelscopeLicense": "mit", "modelscopeParams": 161546240, "modelscopeTags": ["license:mit", "model_type:nanochat", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8592610065}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.256417+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321230", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171252206, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:ms-swift", "custom_tag:LoRA"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2171252206}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.158211+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321227", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952692+00:00", "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171252206, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:ms-swift", "custom_tag:LoRA"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2171252206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.158211+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321227", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033585336, "estimatedRequiredGiB": 2.457, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2198654500, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2198654500}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.452954+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321233", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952361+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033585336, "estimatedRequiredGiB": 2.457, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2198654500, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2198654500}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.452954+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321233", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871536, "estimatedRequiredGiB": 2.418, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2163952661, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2163952661}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.251813+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321228", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952577+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871536, "estimatedRequiredGiB": 2.418, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2163952661, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2163952661}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.251813+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321228", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2856860040, "estimatedRequiredGiB": 3.21, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2872281308, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2872281308}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.359035+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321231", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.951772+00:00", "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2856860040, "estimatedRequiredGiB": 3.21, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2872281308, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2872281308}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.359035+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321231", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "juspay/Xor-26B-A4B-NVFP4", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18788485588, "estimatedRequiredGiB": 21.039, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 18825737204, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14386943566, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 18825737204}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.249551+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321225", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952465+00:00", "modelId": "juspay/Xor-26B-A4B-NVFP4", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18788485588, "estimatedRequiredGiB": 21.039, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 18825737204, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14386943566, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 18825737204}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.249551+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321225", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6343991648, "estimatedRequiredGiB": 7.115, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6366013051, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1716764160, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6366013051}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.444551+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321234", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952019+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6343991648, "estimatedRequiredGiB": 7.115, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6366013051, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1716764160, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6366013051}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.444551+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321234", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2103475788, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:apple-silicon", "custom_tag:oq", "custom_tag:llama", "custom_tag:minicpm", "custom_tag:imatrix", "custom_tag:long-context", "custom_tag:coding", "custom_tag:sharp-template", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2103475788}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.357060+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321232", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952258+00:00", "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2103475788, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:apple-silicon", "custom_tag:oq", "custom_tag:llama", "custom_tag:minicpm", "custom_tag:imatrix", "custom_tag:long-context", "custom_tag:coding", "custom_tag:sharp-template", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2103475788}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.357060+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321232", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "eb9a83ed79f9711dceddc0b4af1fc5cfd921fcd5ee82124559cfc373fff55bf0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.454507+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321236", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952910+00:00", "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "eb9a83ed79f9711dceddc0b4af1fc5cfd921fcd5ee82124559cfc373fff55bf0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.454507+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321236", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19395158128, "estimatedRequiredGiB": 21.699, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 19416072650, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4022513664, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:betterwright", "custom_tag:browser-agent", "custom_tag:web-agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:diffusion-language-model", "custom_tag:uno", "custom_tag:k2-horizon", "custom_tag:full-finetune"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19416072650}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.649801+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321240", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952127+00:00", "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19395158128, "estimatedRequiredGiB": 21.699, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 19416072650, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4022513664, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:betterwright", "custom_tag:browser-agent", "custom_tag:web-agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:diffusion-language-model", "custom_tag:uno", "custom_tag:k2-horizon", "custom_tag:full-finetune"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19416072650}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.649801+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321240", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": 1556071699, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.659479+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321238", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952460+00:00", "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": 1556071699, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.659479+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321238", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-llama-mha-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960168568, "estimatedRequiredGiB": 2.344, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2097293495, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2097293495}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.654563+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321239", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952687+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960168568, "estimatedRequiredGiB": 2.344, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2097293495, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2097293495}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.654563+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321239", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1216600244, "estimatedRequiredGiB": 1.365, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1221756819, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1221756819}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.664357+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321237", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952789+00:00", "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1216600244, "estimatedRequiredGiB": 1.365, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1221756819, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1221756819}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.664357+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321237", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20984462832, "estimatedRequiredGiB": 23.486, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21014909211, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5865901936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:qwen3-next", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:mixture-of-experts"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21014909211}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.660792+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321235", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952571+00:00", "modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20984462832, "estimatedRequiredGiB": 23.486, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21014909211, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5865901936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:qwen3-next", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:mixture-of-experts"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21014909211}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.660792+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321235", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427432, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412809492, "modelscopeLicense": "other", "modelscopeParams": 209741824, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412809492}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.967998+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321245", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952014+00:00", "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427432, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412809492, "modelscopeLicense": "other", "modelscopeParams": 209741824, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412809492}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.967998+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321245", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4749242120, "estimatedRequiredGiB": 5.332, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 4771310100, "modelscopeLicense": "apache-2.0", "modelscopeParams": 641597440, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4771310100}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.763496+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321241", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.953011+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4749242120, "estimatedRequiredGiB": 5.332, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 4771310100, "modelscopeLicense": "apache-2.0", "modelscopeParams": 641597440, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4771310100}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.763496+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321241", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474195, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320426072, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:fp16", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320426072}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.947704+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321243", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.951876+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474195, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320426072, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:fp16", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320426072}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.947704+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321243", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.638, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:thinking", "custom_tag:fable5", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:agentic", "custom_tag:coding", "custom_tag:instruction-following", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5045067151}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.961173+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321246", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952253+00:00", "modelId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.638, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:thinking", "custom_tag:fable5", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:agentic", "custom_tag:coding", "custom_tag:instruction-following", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5045067151}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.961173+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321246", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:51.156951+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321247", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952355+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:51.156951+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321247", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:50.965243+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321242", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.951746+00:00", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.965243+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321242", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23253718728, "estimatedRequiredGiB": 26.013, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 23275790433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779305408, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23275790433}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:51.364169+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5321248", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952906+00:00", "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23253718728, "estimatedRequiredGiB": 26.013, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 23275790433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779305408, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23275790433}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:51.364169+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5321248", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896236664, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898355154, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898355154}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T09:57:51.656942+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321249", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952123+00:00", "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896236664, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898355154, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898355154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:51.656942+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321249", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "webAI-Official/TwIL-LM3-Pro", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517272, "estimatedRequiredGiB": 29.512, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 26407018955, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26407018955}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T10:15:00.765306+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321497", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "webAI-Official/TwIL-LM3-Pro", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517272, "estimatedRequiredGiB": 29.512, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 26407018955, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26407018955}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T10:15:00.765306+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321497", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "webAI-Official/TwIL-LM2", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5067121544, "estimatedRequiredGiB": 20.413, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 18264867356, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:twil-lm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18264867356}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T10:15:00.746034+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321499", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "webAI-Official/TwIL-LM2", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5067121544, "estimatedRequiredGiB": 20.413, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 18264867356, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:twil-lm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18264867356}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T10:15:00.746034+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321499", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 467369015}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T10:15:00.656545+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5321500", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 467369015}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T10:15:00.656545+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5321500", "taskType": "text-generation", "verifyResult": null}