Modelpublic

Shinrali/Qwen3.8-Flash-Next-NVIDIA-Hybrid-FP8-LMHead-Single-Spark

sourceHugging Faceotherupdated 9d agoView on Hugging Face

0likes134downloads

3 commits on main

d07f8d69d ago

Clarify FP8 checkpoint and WSL2 benchmark

Shinrali

2c832cb9d ago

Document RTX PRO 6000 WSL2 benchmark

Shinrali

4abdbbd9d ago

Publish clean NVIDIA hybrid release

Shinrali