diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl
index ea06109bfa..2c5170a43a 100644
--- a/.modelhub_state/recovery_intents.jsonl
+++ b/.modelhub_state/recovery_intents.jsonl
@@ -3486,7 +3486,7 @@
 {"batchId": "0d179088289749ae9a8f59801fd01a18", "completedAt": "2026-10-13T19:48:53.514549+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-10-13T19:47:48.359810+00:00", "framework": "vllm-patch-tokenizer", "intentId": "50ddd462c08a4a6f8d88fd22e428ba93", "lastModified": "2026-10-13T18:29:48+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-24B-A2B-MLX-6bit", "reason": null, "reconciledAt": "2026-10-13T20:10:18.945673+00:00", "repoId": "LiquidAI/LFM2.5-24B-A2B-MLX-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5518412", "taskType": "text-generation"}
 {"batchId": "51f67207f4ff4f33a9986113d38f5090", "completedAt": "2026-10-13T20:02:54.176300+00:00", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-10-13T20:01:57.082920+00:00", "framework": "vllm-mlu", "intentId": "a5f26f0a819b48d791de44052a27fdce", "lastModified": "2026-10-13T18:29:48+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-24B-A2B-MLX-6bit", "reason": null, "reconciledAt": "2026-10-13T20:10:18.945190+00:00", "repoId": "LiquidAI/LFM2.5-24B-A2B-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5518622", "taskType": "text-generation"}
 {"batchId": "51f67207f4ff4f33a9986113d38f5090", "completedAt": "2026-10-13T20:02:54.176315+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-10-13T20:01:57.083096+00:00", "framework": "vllm", "intentId": "d737af60fd704ca48bdf9aa66e337501", "lastModified": "2026-10-13T18:39:46+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-24B-A2B-MLX-8bit", "reason": null, "reconciledAt": "2026-10-13T20:10:18.946077+00:00", "repoId": "LiquidAI/LFM2.5-24B-A2B-MLX-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5518621", "taskType": "text-generation"}
-{"batchId": "61b09aa2406f4e248e2aafc8c5b0c013", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-10-13T20:24:47.258400+00:00", "framework": "vllm", "intentId": "58bcb9b873da4736bfb2fd860ed3b9b1", "lastModified": "2026-10-13T18:29:48+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-24B-A2B-MLX-6bit", "repoId": "LiquidAI/LFM2.5-24B-A2B-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"}
+{"batchId": "61b09aa2406f4e248e2aafc8c5b0c013", "completedAt": "2026-10-13T20:26:18.416220+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-10-13T20:24:47.258400+00:00", "framework": "vllm", "intentId": "58bcb9b873da4736bfb2fd860ed3b9b1", "lastModified": "2026-10-13T18:29:48+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-24B-A2B-MLX-6bit", "reason": null, "repoId": "LiquidAI/LFM2.5-24B-A2B-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "submitted", "targetGpu": "Mthreads_s4000", "taskId": "5519001", "taskType": "text-generation"}
 {"batchId": "64ef2259965a4a47875e42e124456e7a", "completedAt": "2026-10-10T08:22:29.829255+00:00", "configFingerprint": "014e4c7848d2739d8b20b385d6b85827a2fc5723d3b5a17c03afbd67c56275d9", "configSource": "modelhub_live", "createdAt": "2026-10-10T08:19:42.281118+00:00", "framework": "llamacpp", "intentId": "1c4c57e0fcb04deda8bccda4d928eff0", "repoId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Iluvatar_bi-150", "taskId": null, "taskType": "text-generation"}
 {"batchId": "04247231908a4293bb90fcfb6ceb1b21", "completedAt": "2026-10-10T03:37:10.311161+00:00", "configFingerprint": "41b32e99f4cd3b280f48beb66666c48e543570dbfdee61682247438440dae4f3", "configSource": "modelhub_live", "createdAt": "2026-10-10T03:35:16.235834+00:00", "framework": "llamacpp", "intentId": "7ec4fc2708014d83955beed36401eb73", "repoId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "uniqueness_rejected", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
 {"batchId": "defc40efc99547dea797f26d6a4c1a65", "completedAt": "2026-10-10T03:33:51.337890+00:00", "configFingerprint": "b6b49b497726342799df1608aa88399dc2d2712f97d7f1eb9fbc89c5b78f2c4c", "configSource": "modelhub_live", "createdAt": "2026-10-10T03:32:02.289053+00:00", "framework": "llamacpp", "intentId": "4dc3d20711774633bcaa193b5c6032ab", "repoId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-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 4a44126e07..6bddb57c30 100644
--- a/.modelhub_state/routing_intelligence.json
+++ b/.modelhub_state/routing_intelligence.json
@@ -1,6 +1,6 @@
 {
   "acceptedByCategory": {
-    "unified_success_first": 3625
+    "unified_success_first": 3626
   },
   "acceptedByRoute": {
     "text-generation|Ascend_910-b3|llamacpp": 31,
@@ -31,7 +31,7 @@
     "text-generation|MetaX_c-500|vllm": 136,
     "text-generation|MetaX_c-500|vllm_tokenizer_patch": 104,
     "text-generation|Mthreads_s4000|llamacpp": 29,
-    "text-generation|Mthreads_s4000|vllm": 191,
+    "text-generation|Mthreads_s4000|vllm": 192,
     "text-generation|Sunrise_pt-200-x1|vllm": 87,
     "text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 111,
     "text-generation|Vastai_va16|vllm_fix_tokenizer": 103,
@@ -39,8 +39,8 @@
     "text-generation|hygon_k100-ai|vllm": 35,
     "text-generation|hygon_k100-ai|vllm-patch-tokenizer": 235
   },
-  "acceptedSinceRefresh": 3625,
-  "acceptedTotal": 3625,
-  "generatedAt": "2026-10-13T20:02:54.049097+00:00",
+  "acceptedSinceRefresh": 3626,
+  "acceptedTotal": 3626,
+  "generatedAt": "2026-10-13T20:26:18.352699+00:00",
   "version": 1
 }
diff --git a/ledger/submissions.jsonl b/ledger/submissions.jsonl
index 10ff30f8c5..ca44770c1c 100644
--- a/ledger/submissions.jsonl
+++ b/ledger/submissions.jsonl
@@ -1120,3 +1120,4 @@
 {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/XingChen-AGI/Xing4.0-29B-A4B", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "submitTime": "2026-10-13T12:30:24.554632+00:00", "targetGpu": "MetaX_c-500", "taskId": "5512351", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
 {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/XingChen-AGI/Xing4.0-29B-A4B", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "submitTime": "2026-10-13T12:52:58.552750+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5512698", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
 {"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/XingChen-AGI/Xing4.0-29B-A4B", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "submitTime": "2026-10-13T13:12:18.147765+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5513114", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
+{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-24B-A2B-MLX-6bit", "modelId": "LiquidAI/LFM2.5-24B-A2B-MLX-6bit", "submitTime": "2026-10-13T20:24:48.464556+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5519001", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
diff --git a/manifest.json b/manifest.json
index 369fcd5088..a66840507e 100644
--- a/manifest.json
+++ b/manifest.json
@@ -10,16 +10,16 @@
     ".modelhub_state/queue_cleanup_latest.json": "a853c3ecd05b6eb13dc78028071c981c78c9adf73c9831a523b9562a8bdb1610",
     ".modelhub_state/recent_outcomes.jsonl": "d5f3321c7c835be11fc790c6b04936eee563f577da3818cfa5dc8aa7c8332239",
     ".modelhub_state/recovery_active_tasks.jsonl": "51ab670ef6f91958e99955c915f8572ea161fe118c3f7c9a8fd358f4661f8a18",
-    ".modelhub_state/recovery_intents.jsonl": "82138439eae73fb0bd36e507ac5df033545498b28249edb88f8fe7f6828d98c0",
-    ".modelhub_state/routing_intelligence.json": "ed70b37337b7d52d4a7ac680d0186b051f9b3b10c0b55917127ed7134ae1befa",
+    ".modelhub_state/recovery_intents.jsonl": "950bd726b72a6069c7c738bae77e77dd7bc5670d527a0c11beba97592f087234",
+    ".modelhub_state/routing_intelligence.json": "bafe901de169ee115c3f386f342cf7ccb8c1921a9dbe284115e986e59426e138",
     ".modelhub_state/submission_exclusions.jsonl": "660ad77b924d3b0cc76f46aacd1f91a924d13a02bc68057eb5a964647441283b",
     ".modelhub_state/worker_crashes.jsonl": "a6b56caed5c7afeb803f8701393cf4660f7e9799eb5ff84af826a142e16d9b00",
-    "ledger/submissions.jsonl": "c0a1320cab182729d3fe87ab3b1cde377b79ed57841b50ae5e12a0f4a11538f4",
-    "outcomes/submissions.jsonl": "c632c25a9ff019932006a790c8dce349e7d277f1ef4a5beece28bd7840c44ed5"
+    "ledger/submissions.jsonl": "61386ffc247644b9a1341c743297a22d0dbb379bc1c0c58ce76ebd378309538f",
+    "outcomes/submissions.jsonl": "2f702e6738e73eb04b2ae477844a74860f47445dc161cc5ce33e28ec0133ec8d"
   },
-  "generation": 24404,
-  "phase": "intent",
+  "generation": 24405,
+  "phase": "result",
   "schemaVersion": 1,
-  "updatedAt": "2026-10-13T20:24:47.419581+00:00",
+  "updatedAt": "2026-10-13T20:26:18.603721+00:00",
   "writerId": "0b4d13138a434e929040a457f5ff8e93"
 }
diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl
index 619c8411ab..f20abf4523 100644
--- a/outcomes/submissions.jsonl
+++ b/outcomes/submissions.jsonl
@@ -971,3 +971,4 @@
 {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-24B-A2B-MLX-6bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19493321709, "estimatedRequiredGiB": 21.806, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 19511331991, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:moe", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19511331991}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-13T19:47:50.846558+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5518412", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-24B-A2B-MLX-6bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19493321709, "estimatedRequiredGiB": 21.806, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 19511331991, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:moe", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19511331991}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-13T20:01:58.663421+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5518622", "taskType": "text-generation", "verifyResult": null}
 {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-24B-A2B-MLX-8bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25484884997, "estimatedRequiredGiB": 28.502, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 25502895279, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:moe", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25502895279}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-13T20:01:58.646474+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5518621", "taskType": "text-generation", "verifyResult": null}
+{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-24B-A2B-MLX-6bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19493321709, "estimatedRequiredGiB": 21.806, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 19511331991, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:moe", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19511331991}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-13T20:24:48.464556+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5519001", "taskType": "text-generation", "verifyResult": null}