Modelpublic

gratex/Qwen3.8-27B-W4A16-g128-sym-GPTQ

sourceHugging Faceapache-2.0updated 25d agoView on Hugging Face

0likes397downloads

4 commits on main

ff953a625d ago

Add downstream task benchmarks (lm-evaluation-harness v0.4.12, 16 suites)

ebircak

349f6531mo ago

Upload Qwen3.8-27B W4A16 g128 symmetric GPTQ quantization (v9-2)

ebircak

9d7c4b91mo ago

Upload README.md with huggingface_hub

ebircak

53dfc6f1mo ago

initial commit

ebircak