Modelpublic

meteorain/Qwen3-4B-Thinking-2507-llmc-gptq-calib-math-code-science-w4a16-g128-n256-s1024

sourceHugging Faceupdated 3mo agoView on Hugging Face

0likes8downloads

Model Card

Qwen3-4B-Thinking-2507-llmc-gptq-calib-math-code-science-w4a16-g128-n256-s1024

Base model: Qwen/Qwen3-4B-Thinking-2507

Quantized with llm-compressor.

—method: gptq
—weight format: W4A16
—group size: 128
—calibration dataset: nvidia/Llama-Nemotron-Post-Training-Dataset
—calibration split: math,code,science
—calibration samples: 256
—max sequence length: 1024