doth4580
/

Qwen3.5-9B-NVFP4-FULL

compressed-tensors

8-bit precision

Model card Files Files and versions

Qwen3.5-9B-NVFP4-FULL / preprocessor_config.json

Commit History

NVFP4/FP8-quantized 9b-nvfp4-full for veloGB10 (NVIDIA DGX Spark / GB10)

f7b7208
verified

doth4580 commited on 11 days ago