RadixArk
/

Qwen3.8-27B-NVFP4

Image-Text-to-Text

Model Optimizer

Model card Files Files and versions

Resources

View closed (0)

The DFlash2 restriction behind the BF16 lm_head change was removed upstream a day earlier

#3 opened 7 days ago by

Win11 Docker vLLM RTX5090 32G显存 32G内存推荐部署方案

#2 opened 9 days ago by

DSpark for NVFP4

#1 opened 14 days ago by