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

  • Log In
  • Sign Up

eousphoros
/
DeepSeek-V3.2-NVFP4

Text Generation
Transformers
Safetensors
deepseek_v32
nvfp4
fp4
quantized
deepseek
Mixture of Experts
8-bit precision
modelopt
Model card Files Files and versions
xet
Community
3
New discussion
Resources
  • PR & discussions documentation
  • Code of Conduct
  • Hub documentation

Is it possible to make smaller NVFP4 quant at 340-360GB to fit in 4x96gb?

👍 1
61
#1 opened 7 days ago by
Fernanda24

Wondering how could you tested this with 2xRTX 6000 pro

4
#2 opened 7 days ago by
csabakecskemeti

How did you bypass deepseek-v32 not recognized in Tranformers?

3
#3 opened 6 days ago by
Fernanda24
Company
TOS Privacy About Jobs
Website
Models Datasets Spaces Pricing Docs