lhoang8500
/

Qwen3-VL-8B-Instruct-NVFP4

8-bit precision

compressed-tensors

Model card Files Files and versions

Qwen3-VL-8B-Instruct-NVFP4 / quantize.py

Commit History

Create quantize.py

b707c8c
verified

lhoang8500 commited on Nov 7, 2025