diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl
index 39474f571b..3846f03b5c 100644
--- a/.modelhub_state/recovery_intents.jsonl
+++ b/.modelhub_state/recovery_intents.jsonl
@@ -953,9 +953,9 @@
 {"batchId": "e870b856c7764240a368caf6f31f521e", "completedAt": "2026-09-19T13:54:53.384953+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-19T13:54:46.846994+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0ff6a3413656475aaf1cb5eba197bd45", "lastModified": "2026-09-13T05:35:22+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Spark-X2.5-4B-OptiQ-4bit", "reason": null, "reconciledAt": "2026-09-19T16:34:09.257001+00:00", "repoId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4957862", "taskType": "text-generation"}
 {"batchId": "9bec1f927ab54452924beb3334768958", "completedAt": "2026-09-19T14:12:25.691740+00:00", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-09-19T14:12:16.083824+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "df8948ffc6854ff1b577c7f872927aaf", "lastModified": "2026-09-13T05:35:22+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Spark-X2.5-4B-OptiQ-4bit", "reason": null, "reconciledAt": "2026-09-19T16:34:09.256256+00:00", "repoId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_bi-150", "taskId": "4958152", "taskType": "text-generation"}
 {"batchId": "bf5941861b944640b6b5ae365949bd2e", "completedAt": "2026-09-19T14:29:47.756113+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-19T14:29:41.246741+00:00", "framework": "vllm", "intentId": "129b9ae701b2478e8668af291cfd0777", "lastModified": "2026-09-13T05:35:22+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Spark-X2.5-4B-OptiQ-4bit", "reason": null, "reconciledAt": "2026-09-19T16:34:09.256616+00:00", "repoId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_mrv-100", "taskId": "4958426", "taskType": "text-generation"}
-{"batchId": "75da9fe5c33f4b088e8540f801803e73", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-19T16:40:48.731555+00:00", "framework": "vllm-mlu", "intentId": "e801cbf9315145c9affb6987081fac67", "lastModified": "2026-09-13T05:35:22+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Spark-X2.5-4B-OptiQ-4bit", "repoId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
-{"batchId": "75da9fe5c33f4b088e8540f801803e73", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-19T16:40:48.731655+00:00", "framework": "vllm_fix_tokenizer", "intentId": "762cbdab35b54ed684f8b85f245e3ea2", "lastModified": "2026-09-19T14:04:43+00:00", "modelAddress": "https://modelscope.cn/models/logic65/Whittle-Qwen-3.8-35B-A3B", "repoId": "logic65/Whittle-Qwen-3.8-35B-A3B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
-{"batchId": "75da9fe5c33f4b088e8540f801803e73", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-19T16:40:48.731704+00:00", "framework": "vllm", "intentId": "b5bcbeeab06a430ebdb4bf5cba7b4a8d", "lastModified": "2026-09-19T12:07:43+00:00", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "repoId": "Arain119/Sophia", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"}
+{"batchId": "75da9fe5c33f4b088e8540f801803e73", "completedAt": "2026-09-19T16:41:09.029864+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-09-19T16:40:48.731555+00:00", "framework": "vllm-mlu", "intentId": "e801cbf9315145c9affb6987081fac67", "lastModified": "2026-09-13T05:35:22+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Spark-X2.5-4B-OptiQ-4bit", "reason": null, "repoId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "submitted", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4960316", "taskType": "text-generation"}
+{"batchId": "75da9fe5c33f4b088e8540f801803e73", "completedAt": "2026-09-19T16:41:09.029877+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-19T16:40:48.731655+00:00", "framework": "vllm_fix_tokenizer", "intentId": "762cbdab35b54ed684f8b85f245e3ea2", "lastModified": "2026-09-19T14:04:43+00:00", "modelAddress": "https://modelscope.cn/models/logic65/Whittle-Qwen-3.8-35B-A3B", "reason": null, "repoId": "logic65/Whittle-Qwen-3.8-35B-A3B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Kunlunxin_p-800", "taskId": "4960317", "taskType": "text-generation"}
+{"batchId": "75da9fe5c33f4b088e8540f801803e73", "completedAt": "2026-09-19T16:41:09.029880+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-09-19T16:40:48.731704+00:00", "framework": "vllm", "intentId": "b5bcbeeab06a430ebdb4bf5cba7b4a8d", "lastModified": "2026-09-19T12:07:43+00:00", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "reason": null, "repoId": "Arain119/Sophia", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Mthreads_s4000", "taskId": "4960315", "taskType": "text-generation"}
 {"batchId": "4cc812b7f6074338b0c6ed46bdd2672b", "completedAt": "2026-09-19T04:58:26.492770+00:00", "configFingerprint": "c240df8c4ef51c3028e28d4dbd670173f9ac1f001d6c73625ec2cdaccb288665", "configSource": "modelhub_live", "createdAt": "2026-09-19T04:58:15.480275+00:00", "framework": "llamacpp", "intentId": "ee86b2205fef40f298072ec892726538", "repoId": "voconly/parakeet-unified-en-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
 {"batchId": "8d27d6d5a99748efbdd97223e640c598", "completedAt": "2026-09-18T14:35:12.136557+00:00", "configFingerprint": "359725c5cf0821e26681bc436dad944747db4ac72a1bf9e70b5f6f8e63a023b4", "configSource": "modelhub_live", "createdAt": "2026-09-18T14:35:06.015304+00:00", "framework": "llamacpp", "intentId": "10303336f4f24e2f98aa86764cc2f0fc", "repoId": "voconly/parakeet-unified-en-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "uniqueness_rejected", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
 {"batchId": "bfd8069a25c5437f87c1eb1f45b313b1", "completedAt": "2026-09-18T14:33:31.434713+00:00", "configFingerprint": "e1276bf11e548198418262ddca64a6c4514301bb26e65ecc7e04f8d8f0442b6b", "configSource": "modelhub_live", "createdAt": "2026-09-18T14:33:23.815503+00:00", "framework": "llamacpp", "intentId": "3c35cff71fae4e2997f1d1fa492cdda8", "repoId": "voconly/parakeet-unified-en-0.6b-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
diff --git a/.modelhub_state/routing_intelligence.json b/.modelhub_state/routing_intelligence.json
index fa2fd5d530..a61362bad3 100644
--- a/.modelhub_state/routing_intelligence.json
+++ b/.modelhub_state/routing_intelligence.json
@@ -1,6 +1,6 @@
 {
   "acceptedByCategory": {
-    "unified_success_first": 1088
+    "unified_success_first": 1091
   },
   "acceptedByRoute": {
     "text-generation|Ascend_910-b3|llamacpp": 17,
@@ -10,25 +10,25 @@
     "text-generation|Ascend_910-b4|vllm_tokenizer_patch": 49,
     "text-generation|Biren_166m|vllm": 59,
     "text-generation|Biren_166m|vllm_fix_tokenizer": 13,
-    "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 47,
+    "text-generation|Cambricon_mlu-370-x4|vllm-mlu": 48,
     "text-generation|Cambricon_mlu-370-x8|vllm": 13,
     "text-generation|Cambricon_mlu-370-x8|vllm-customized": 10,
     "text-generation|Cambricon_mlu-370-x8|vllm-mlu": 76,
     "text-generation|Iluvatar_bi-150|llamacpp": 16,
     "text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 81,
     "text-generation|Iluvatar_mrv-100|vllm": 56,
-    "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 124,
+    "text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 125,
     "text-generation|MetaX_c-500|vllm": 99,
     "text-generation|Mthreads_s4000|llamacpp": 17,
-    "text-generation|Mthreads_s4000|vllm": 81,
+    "text-generation|Mthreads_s4000|vllm": 82,
     "text-generation|Sunrise_pt-200-x1|vllm": 62,
     "text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 62,
     "text-generation|Vastai_va16|vllm_fix_tokenizer": 50,
     "text-generation|hygon_k100-ai|llamacpp": 17,
     "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 63
   },
-  "acceptedSinceRefresh": 1088,
-  "acceptedTotal": 1088,
-  "generatedAt": "2026-09-19T14:29:47.727861+00:00",
+  "acceptedSinceRefresh": 1091,
+  "acceptedTotal": 1091,
+  "generatedAt": "2026-09-19T16:41:09.000299+00:00",
   "version": 1
 }
diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl
index 570210190f..e29c357db8 100644
--- a/ledger/submissions.jsonl
+++ b/ledger/submissions.jsonl
@@ -695,3 +695,6 @@
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "submitTime": "2026-09-09T21:08:22.097030+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746441", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "submitTime": "2026-09-15T04:40:55.440325+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4866579", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
 {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "submitTime": "2026-09-15T04:40:55.438125+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4866581", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
+{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/mlx-community/Spark-X2.5-4B-OptiQ-4bit", "modelId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "submitTime": "2026-09-19T16:40:56.574545+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4960316", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
+{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/logic65/Whittle-Qwen-3.8-35B-A3B", "modelId": "logic65/Whittle-Qwen-3.8-35B-A3B", "submitTime": "2026-09-19T16:40:56.513852+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4960317", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Arain119/Sophia", "modelId": "Arain119/Sophia", "submitTime": "2026-09-19T16:40:56.572866+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4960315", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
diff --git a/manifest.json b/manifest.json
index ea47c289f8..0c1e452c81 100644
--- a/manifest.json
+++ b/manifest.json
@@ -9,16 +9,16 @@
     ".modelhub_state/queue_cleanup_latest.json": "098ad0f379328064441a9b54788e583c3ab29b0ed1148d04f4aa78b7f95ed409",
     ".modelhub_state/recent_outcomes.jsonl": "2fae2359f00256e76fd8cc884daa5230e899c5fb80cc059aa9b2c78663afbd10",
     ".modelhub_state/recovery_active_tasks.jsonl": "5d3956df82c4ca9b28b2d532765085bbfa6708f84945f9588cd0a1fd70ca494e",
-    ".modelhub_state/recovery_intents.jsonl": "b9d14b8cb3f3c4e32c3ee9fd3371c4fdd945f5d4bf4920b54b63953beebf8996",
-    ".modelhub_state/routing_intelligence.json": "cec8672f896fc36e594bc040d19fead43456bb90c87b29e3177b8de356eb59dd",
+    ".modelhub_state/recovery_intents.jsonl": "364a25a212c4518d511fed405dbd0d50ba45e042bfce444a515913c683e91c74",
+    ".modelhub_state/routing_intelligence.json": "5611c854b50cb91dd694dee876b6ac805cf418c31086d90de2423a6bc3b1309e",
     ".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
     ".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
-    "ledger/submissions.jsonl": "73fdba60dc9cf1c41de124a983cbeaa698f9b0f87da302739d7bd2333d40978a",
-    "outcomes/submissions.jsonl": "127f069e9e3eef4072bc71ea5334ad3b21aaa1284bfdfe81d55f8fe507004edf"
+    "ledger/submissions.jsonl": "bec11ea8a11a756302c7ff37313c661401b33ead67157ba6c90e0e00aa1f3e89",
+    "outcomes/submissions.jsonl": "c59b10c8b45e16b3b6fcb2acc33e849d89592d44f095ac22a236d524cad529ec"
   },
-  "generation": 9902,
-  "phase": "intent",
+  "generation": 9903,
+  "phase": "result",
   "schemaVersion": 1,
-  "updatedAt": "2026-09-19T16:40:48.811916+00:00",
+  "updatedAt": "2026-09-19T16:41:09.137450+00:00",
   "writerId": "b4717c3c30654a5585d5941286742f58"
 }
diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl
index 4ce7523953..2471b7fb4b 100644
--- a/outcomes/submissions.jsonl
+++ b/outcomes/submissions.jsonl
@@ -497,3 +497,6 @@
 {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3040272206, "estimatedRequiredGiB": 3.409, "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": 3050595322, "modelscopeLicense": "apache-2.0", "modelscopeParams": 824389120, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_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:spark2_5", "custom_tag:long-context"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3050595322}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-19T13:54:47.552192+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4957862", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": null, "modelId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3040272206, "estimatedRequiredGiB": 3.409, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3050595322, "modelscopeLicense": "apache-2.0", "modelscopeParams": 824389120, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_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:spark2_5", "custom_tag:long-context"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3050595322}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-19T14:12:16.848758+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4958152", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3040272206, "estimatedRequiredGiB": 3.409, "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": 3050595322, "modelscopeLicense": "apache-2.0", "modelscopeParams": 824389120, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_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:spark2_5", "custom_tag:long-context"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3050595322}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-19T14:29:41.941767+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4958426", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3040272206, "estimatedRequiredGiB": 3.409, "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": 3050595322, "modelscopeLicense": "apache-2.0", "modelscopeParams": 824389120, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_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:spark2_5", "custom_tag:long-context"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3050595322}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-19T16:40:56.574545+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4960316", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "logic65/Whittle-Qwen-3.8-35B-A3B", "modelProfile": {"architectures": ["Qwen4ExpForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 71124871192, "estimatedRequiredGiB": 79.514, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen4_exp_text", "modelscopeFileSize": 71148270844, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27568130195, "modelscopeTags": ["license:apache-2.0", "model_type:qwen4_exp_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:whittle", "custom_tag:qwen4_exp", "custom_tag:mixture-of-experts", "custom_tag:moe", "custom_tag:n-gram-memory", "custom_tag:conditional-memory", "custom_tag:hyper-connections", "custom_tag:knowledge-distillation", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:code", "custom_tag:math", "custom_tag:llama.cpp", "custom_tag:safetensors", "custom_tag:text-generation", "custom_tag:conversational", "custom_tag:research"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 71148270844}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-19T16:40:56.513852+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4960317", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-19T16:40:56.572866+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4960315", "taskType": "text-generation", "verifyResult": null}