amd / DeepSeek-R1-MXFP4

Other371B43.2K5Updated Apr 13, 2026

Downloads

43.2K

Likes

5

Last updated

Apr 13, 2026

License

mit

- Model Architecture: DeepSeek-R1 - Input: Text - Output: Text - Supported Hardware Microarchitecture: AMD MI350/MI355 - ROCm: 7.0 - PyTorch: 2.8.0 - Transformers: 4.53.0 - Operating System(s): Linux - Inference Engine: SGLang - Model Optimizer: AMD-Quark (V0.10) - Weight quan…

Tags

  • deepseek_v3
  • custom_code
  • 8-bit
  • quark

Technical specifications

Parameters371B
LibraryNot available
LanguagesNot available
Licensemit