Qwen3.8-Flash-Next-NVFP4 / conversion_environment.json
justintong
Qwen3.8-Flash-Next-NVFP4: NVFP4 routed experts + FP8 PLE (135GB)
7b71922
Raw
History Blame Contribute Delete
344 Bytes
{
"accelerate": "1.14.0",
"cuda": "13.0",
"datasets": "5.0.1",
"modelopt_clean": true,
"modelopt_commit": "87c9f8cf83021957d1a1a575c90c9a4eaaf7ef0c",
"modelopt_distribution": "nvidia-modelopt",
"modelopt_version": "0.46.0",
"python": "3.12.3",
"pytorch": "2.13.0+cu130",
"safetensors": "0.8.0",
"transformers": "5.12.1"
}