hugpadhugpad

amd / Qwen3.8-2.4T-A95B-Quark-MXFP4

Text Generation1248B16.2K6Updated Aug 14, 2026
Hugging Face

Downloads

16.2K

Likes

6

Last updated

Aug 14, 2026

License

Not available

- Model Architecture: Qwen35MoeForCausalLM - Input: Text - Output: Text - Supported Hardware Microarchitecture: AMD MI350 / MI355 - ROCm: 7.2.0 - PyTorch: 2.12.0 - Transformers: 5.14.1 - Operating System(s): Linux - Inference Engine: SGLang/vLLM - Model Optimizer: AMD-Quark (v…

Tasks & library

  • text generation
  • transformers

Tags

  • transformers
  • qwen3_5_moe_text
  • text-generation
  • conversational
  • en
  • 8-bit

Technical specifications

Parameters1248B
Librarytransformers
Languagesen
Base modelQwen/Qwen3.8-2.4T-A95B-FP8
LicenseNot available