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

Vision20B903.8K132Updated Jul 12, 2026

Downloads

903.8K

Likes

132

Last updated

Jul 12, 2026

License

apache-2.0

1.79x faster throughput than other NVFP4 quants. This is an Unsloth NVFP4 quantized checkpoint calibrated on a mixture of our Unsloth dataset + UltraChat dataset. Works on a 32GB VRAM GPU. Benchmarks on 1xB200 128 concurrency.

Tasks & library

  • image text to text
  • transformers

Tags

  • transformers
  • qwen3_5_moe
  • image-text-to-text
  • unsloth
  • qwen
  • qwen3_5

Technical specifications

Parameters20B
Librarytransformers
LanguagesNot available
Licenseapache-2.0