STILLWORKS

Qwen3.6-35B-A3B-NVFP4-Fast

image-text-to-text model on Hugging Face

Visit product ↗
AI tools HF Models Launched Jul 10, 2026 by unsloth View original post ↗

Unsloth's fast NVFP4 build of Qwen 3.6 35B MoE.

image-text-to-text

Potential upside

  • Combines a strong base (Qwen 3.6), efficient MoE, and Unsloth optimization
  • NVFP4 targets real speed on modern NVIDIA cards

Worth watching

  • NVFP4 benefit needs matching hardware; a repackage, not new capability

A first look, not a review — this product just launched and has no user history yet. We flag what looks promising and what to check before you rely on it.

Who it's for

NVIDIA-equipped teams wanting Qwen 3.6 running fast.

More AI tools