hugpadhugpad

amd / gpt-oss-120b-w-mxfp4-a-fp8

Other59B4.9K10Updated Jun 4, 2026
Hugging Face

Downloads

4.9K

Likes

10

Last updated

Jun 4, 2026

License

apache-2.0

- Model Architecture: gpt-oss-120b - Input: Text - Output: Text - Supported Hardware Microarchitecture: AMD MI350/MI355 - ROCm: 7.0 - Operating System(s): Linux - Inference Engine: vLLM - Model Optimizer: AMD-Quark - Weight quantization: OCP MXFP4, Static - Activation quantiza…

Tags

  • gpt_oss
  • 8-bit
  • quark

Technical specifications

Parameters59B
LibraryNot available
LanguagesNot available
Base modelopenai/gpt-oss-120b
Licenseapache-2.0