doth4580
/

Qwen3.5-27B-NVFP4-FULL

compressed-tensors

8-bit precision

Model card Files Files and versions

Qwen3.5-27B-NVFP4-FULL

Commit History

Upload README.md with huggingface_hub

6cfb913
verified

doth4580 commited on 8 days ago

NVFP4/FP8-quantized 27b-nvfp4-full for veloGB10 (NVIDIA DGX Spark / GB10)

10fb3cf
verified

doth4580 commited on 12 days ago

initial commit

09c4f56
verified

doth4580 commited on 12 days ago