Modelpublic

amd-satre/Qwen3.6-35B-A3B-MXFP4-MOE-GPTQ

sourceHugging Faceapache-2.0updated 2mo agoView on Hugging Face

0likes64downloads

6 commits on main

4b01b8e2mo ago

Upload README.md with huggingface_hub

amd-satre

ba4e9a82mo ago

Upload README.md with huggingface_hub

amd-satre

122adfa2mo ago

Regenerate model card from checkpoint quantization_config

amd-satre

40ab3682mo ago

Fix MoE topology in card: 40 layers x 256 experts (not 80 x 128)

amd-satre

319c6162mo ago

Add Qwen3.6-35B-A3B-MXFP4-MOE-GPTQ

amd-satre

ef2a37e2mo ago

initial commit

amd-satre