22 lines
600 B
JSON
22 lines
600 B
JSON
{
|
|
"track": "gpu",
|
|
"current_model": "devstral-small-2:24b",
|
|
"model_index": 0,
|
|
"phase": "context_scaling",
|
|
"backend": "ollama",
|
|
"current_config": {
|
|
"num_ctx": 32768,
|
|
"num_gpu": 99,
|
|
"flash_attn": true
|
|
},
|
|
"best_configs": {
|
|
"gpu": {},
|
|
"ram": {}
|
|
},
|
|
"completed_models": [],
|
|
"gpu_queue": ["devstral-small-2:24b", "qwen2.5-coder:32b", "codellama:34b-instruct"],
|
|
"ram_queue": ["qwen2.5:72b", "nemotron-3-nano:30b", "mixtral:8x7b-instruct"],
|
|
"context_steps": [32768, 65536, 98304, 131072, 163840, 200704, 262144, 327680],
|
|
"last_updated": "2026-04-28T17:00:00Z"
|
|
}
|