38 lines
1.1 KiB
JSON
38 lines
1.1 KiB
JSON
{
|
|
"verified_at": "2026-08-31",
|
|
"host": "Apple M4 Max, arm64, macOS 15.6",
|
|
"ollama": {
|
|
"version": "0.32.14",
|
|
"mlx_version": "0.32.0-213-gadf21de",
|
|
"device": "gpu",
|
|
"metal_library": true,
|
|
"nvfp4_model": {
|
|
"name": "qwen3.8:27b-mlx",
|
|
"id": "5642e97495e1",
|
|
"format": "safetensors",
|
|
"quantization": "nvfp4",
|
|
"parameter_size": "27.8B",
|
|
"runner_log": "starting mlx runner subprocess"
|
|
},
|
|
"mxfp8_model": {
|
|
"name": "qwen3.8:27b-mxfp8",
|
|
"id": "464021588235",
|
|
"format": "safetensors",
|
|
"quantization": "mxfp8",
|
|
"parameter_size": "27.8B",
|
|
"runner_log": "starting mlx runner subprocess"
|
|
}
|
|
},
|
|
"vllm_metal": {
|
|
"vllm_version": "0.28.0+cpu",
|
|
"plugin_version": "0.4.0.dev20260831112704",
|
|
"mlx_version": "0.32.0",
|
|
"mlx_lm_version": "0.31.3",
|
|
"mlx_vlm_version": "0.6.4",
|
|
"platform_plugin": "metal",
|
|
"compute_log": "MLX device set to: Device(gpu, 0)",
|
|
"pytorch_device_log": "PyTorch device set to: mps",
|
|
"note": "The +cpu suffix identifies the portable vLLM core wheel; the Metal plugin supplies MLX GPU execution."
|
|
}
|
|
}
|