vibe-lm
Public
Project Files
benchmark / results / run-remote-all.log
[2026-07-10T23:30:32.863Z] Starting REMOTE benchmark run 2026-07-10T23-30-32-862Z, standard config: {"contextLength":262144,"flashAttention":true,"llamaKCacheQuantizationType":"q4_0","llamaVCacheQuantizationType":"q4_0","offloadKVCacheToGpu":false,"keepModelInMemory":false,"numExperts":8}
[2026-07-10T23:30:32.879Z] Loading remote:nemotron-3-nano (nvidia/nemotron-3-nano-omni) with STANDARD_LOAD_CONFIG...
[2026-07-10T23:30:33.733Z] FAILED to load remote:nemotron-3-nano:
┌ Error ──────────────────────────────────────────────────────────────────────┐
│ │
│ Model loading was stopped due to insufficient system resources. Under │
│ the current settings, this model requires approximately 25.81 GB of │
│ memory, and continuing to load it would likely overload your system and │
│ cause it to freeze. If you think this is incorrect, you can adjust the │
│ model loading guardrails in settings. │
│ │
│ │
│ </> STACK TRACE │
│ │
│ at benchmarkOneModel (file:///Users/drunkktoys/Desktop/vibeLM/benchmark │
│ /run-remote-all.mjs:136:18) │
│ at main (file:///Users/drunkktoys/Desktop/vibeLM/benchmark/run-remote-a │
│ ll.mjs:178:11) │
│ at file:///Users/drunkktoys/Desktop/vibeLM/benchmark/run-remote-all.mjs │
│ :183:1 │
│ at ModuleJob.run (node:internal/modules/esm/module_job:343:25) │
│ at async onImport.tracePromise.__proto__ │
│ (node:internal/modules/esm/loader:681:26) │
│ at async asyncRunEntryPointWithESMLoader │
│ (node:internal/modules/run_main:117:5) │
│ │
└─────────────────────────────────────────────────────────────────────────────┘
[2026-07-10T23:30:33.734Z] Loading remote:qwen3.6-35b-a3b (qwen/qwen3.6-35b-a3b) with STANDARD_LOAD_CONFIG...
[2026-07-10T23:30:34.619Z] FAILED to load remote:qwen3.6-35b-a3b:
┌ Error ──────────────────────────────────────────────────────────────────────┐
│ │
│ Model loading was stopped due to insufficient system resources. Under │
│ the current settings, this model requires approximately 23.11 GB of │
│ memory, and continuing to load it would likely overload your system and │
│ cause it to freeze. If you think this is incorrect, you can adjust the │
│ model loading guardrails in settings. │
│ │
│ │
│ </> STACK TRACE │
│ │
│ at benchmarkOneModel (file:///Users/drunkktoys/Desktop/vibeLM/benchmark │
│ /run-remote-all.mjs:136:18) │
│ at main (file:///Users/drunkktoys/Desktop/vibeLM/benchmark/run-remote-a │
│ ll.mjs:178:11) │
│ at process.processTicksAndRejections │
│ (node:internal/process/task_queues:103:5) │
│ │
└─────────────────────────────────────────────────────────────────────────────┘
[2026-07-10T23:30:34.620Z] Loading remote:qwen3-coder-30b (qwen/qwen3-coder-30b) with STANDARD_LOAD_CONFIG...
[2026-07-10T23:30:35.423Z] FAILED to load remote:qwen3-coder-30b:
┌ Error ──────────────────────────────────────────────────────────────────────┐
│ │
│ Model loading was stopped due to insufficient system resources. Under │
│ the current settings, this model requires approximately 20.02 GB of │
│ memory, and continuing to load it would likely overload your system and │
│ cause it to freeze. If you think this is incorrect, you can adjust the │
│ model loading guardrails in settings. │
│ │
│ │
│ </> STACK TRACE │
│ │
│ at benchmarkOneModel (file:///Users/drunkktoys/Desktop/vibeLM/benchmark │
│ /run-remote-all.mjs:136:18) │
│ at main (file:///Users/drunkktoys/Desktop/vibeLM/benchmark/run-remote-a │
│ ll.mjs:178:11) │
│ at process.processTicksAndRejections │
│ (node:internal/process/task_queues:103:5) │
│ │
└─────────────────────────────────────────────────────────────────────────────┘
[2026-07-10T23:30:35.423Z] Loading remote:glm-4.7-flash (zai-org/glm-4.7-flash) with STANDARD_LOAD_CONFIG...
[2026-07-10T23:30:35.654Z] FAILED to load remote:glm-4.7-flash:
┌ Error ──────────────────────────────────────────────────────────────────────┐
│ │
│ Model loading was stopped due to insufficient system resources. Under │
│ the current settings, this model requires approximately 18.51 GB of │
│ memory, and continuing to load it would likely overload your system and │
│ cause it to freeze. If you think this is incorrect, you can adjust the │
│ model loading guardrails in settings. │
│ │
│ │
│ </> STACK TRACE │
│ │
│ at benchmarkOneModel (file:///Users/drunkktoys/Desktop/vibeLM/benchmark │
│ /run-remote-all.mjs:136:18) │
│ at main (file:///Users/drunkktoys/Desktop/vibeLM/benchmark/run-remote-a │
│ ll.mjs:178:11) │
│ at process.processTicksAndRejections │
│ (node:internal/process/task_queues:103:5) │
│ │
└─────────────────────────────────────────────────────────────────────────────┘
[2026-07-10T23:30:35.654Z] Loading remote:qwen3.6-27b (qwen/qwen3.6-27b) with STANDARD_LOAD_CONFIG...
[2026-07-10T23:30:35.843Z] FAILED to load remote:qwen3.6-27b:
┌ Error ──────────────────────────────────────────────────────────────────────┐
│ │
│ Model loading was stopped due to insufficient system resources. Under │
│ the current settings, this model requires approximately 25.04 GB of │
│ memory, and continuing to load it would likely overload your system and │
│ cause it to freeze. If you think this is incorrect, you can adjust the │
│ model loading guardrails in settings. │
│ │
│ │
│ </> STACK TRACE │
│ │
│ at benchmarkOneModel (file:///Users/drunkktoys/Desktop/vibeLM/benchmark │
│ /run-remote-all.mjs:136:18) │
│ at main (file:///Users/drunkktoys/Desktop/vibeLM/benchmark/run-remote-a │
│ ll.mjs:178:11) │
│ at process.processTicksAndRejections │
│ (node:internal/process/task_queues:103:5) │
│ │
└─────────────────────────────────────────────────────────────────────────────┘
[2026-07-10T23:30:35.844Z] Loading remote:gemma-4-26b-a4b (google/gemma-4-26b-a4b-qat) with STANDARD_LOAD_CONFIG...
[2026-07-10T23:30:36.030Z] FAILED to load remote:gemma-4-26b-a4b:
┌ Error ──────────────────────────────────────────────────────────────────────┐
│ │
│ Model loading was stopped due to insufficient system resources. │
│ Continuing to load the model would likely overload your system and │
│ cause it to freeze. If you think this is incorrect, you can adjust the │
│ model loading guardrails in settings. │
│ │
│ │
│ </> STACK TRACE │
│ │
│ at benchmarkOneModel (file:///Users/drunkktoys/Desktop/vibeLM/benchmark │
│ /run-remote-all.mjs:136:18) │
│ at main (file:///Users/drunkktoys/Desktop/vibeLM/benchmark/run-remote-a │
│ ll.mjs:178:11) │
│ at process.processTicksAndRejections │
│ (node:internal/process/task_queues:103:5) │
│ │
└─────────────────────────────────────────────────────────────────────────────┘
[2026-07-10T23:30:36.031Z] Loading remote:gpt-oss-20b (openai/gpt-oss-20b) with STANDARD_LOAD_CONFIG...
[2026-07-10T23:30:36.256Z] FAILED to load remote:gpt-oss-20b:
┌ Error ──────────────────────────────────────────────────────────────────────┐
│ │
│ Model loading was stopped due to insufficient system resources. Under │
│ the current settings, this model requires approximately 13.12 GB of │
│ memory, and continuing to load it would likely overload your system and │
│ cause it to freeze. If you think this is incorrect, you can adjust the │
│ model loading guardrails in settings. │
│ │
│ │
│ </> STACK TRACE │
│ │
│ at benchmarkOneModel (file:///Users/drunkktoys/Desktop/vibeLM/benchmark │
│ /run-remote-all.mjs:136:18) │
│ at main (file:///Users/drunkktoys/Desktop/vibeLM/benchmark/run-remote-a │
│ ll.mjs:178:11) │
│ at process.processTicksAndRejections │
│ (node:internal/process/task_queues:103:5) │
│ │
└─────────────────────────────────────────────────────────────────────────────┘
[2026-07-10T23:30:36.257Z] Loading remote:gemma-4-e4b (google/gemma-4-e4b) with STANDARD_LOAD_CONFIG...
[2026-07-10T23:30:50.054Z] [remote:gemma-4-e4b] running arith-1...
[2026-07-10T23:31:09.662Z] [remote:gemma-4-e4b] running arith-2...