Repository navigation

Qwen3.6-35B-A3B on CUDA: draft NVIDIA's NVFP4 checkpoint with a DFlash2 model - #1674

Merged

ashhart merged 1 commit into

ashhart:mainfrom

laudney:pr-q36-dflash2

Oct 31, 2026

Merged

Qwen3.6-35B-A3B on CUDA: draft NVIDIA's NVFP4 checkpoint with a DFlash2 model#1674
ashhart merged 1 commit into
ashhart:mainfrom
laudney:pr-q36-dflash2

Commits on Oct 31, 2026
- feat(qwen3_5): let the MoE target draft with a DFlash2 model
  
  laudney
  authored and
  ashhart
  committed
  50a41a6