Hugging Face's logo Hugging Face
  • Models
  • Datasets
  • Spaces
  • Buckets new
  • Docs
  • Enterprise
  • Pricing

  • Log In
  • Sign Up

nvidia
/
Qwen3.5-397B-A17B-NVFP4

Text Generation
Safetensors
Model Optimizer
qwen3_5_moe
nvidia
ModelOpt
Qwen3.5
quantized
FP4
fp4
conversational
modelopt
Model card Files Files and versions
xet
Community
10
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Is MTP supported by this model?

#10 opened 21 days ago by
Bronyaaa

Please, we need NVFP4 versions that are official and tested against original Qwen3.5 model(s)

#8 opened about 1 month ago by
GabrielaCats

## Real-World Performance on 4x RTX PRO 6000 (SM120) -- Honest Numbers

❀️ 5
3
#7 opened about 2 months ago by
brandonmusic

27B NVFP4 PLEASE

πŸ‘€ 1
2
#6 opened about 2 months ago by
berkerdooo

NVFP4 for Qwen3.5-27B

βž• 1
9
#5 opened 2 months ago by
faheemraza1

Please release a checkpoint for Qwen/Qwen3.5-122B-A10B

βž•πŸ‘ 4
3
#4 opened 2 months ago by
Qnibbles

How to run on SM120

❀️ 3
#3 opened 2 months ago by
catid

Support SM120

β€οΈπŸ‘ 19
6
#2 opened 2 months ago by
darkstar3537

Getting nvidia/Qwen3.5-397B-A17B-NVFP4 running with SGLang (requires transformers v5) on RTX PRO 6000 (blackwell) CUDA 12.9

πŸ”₯ 1
6
#1 opened 2 months ago by
bullpoint
Company
TOS Privacy About Careers
Website
Models Datasets Spaces Pricing Docs