meteorain/Qwen3-4B-Thinking-2507-llmc-gptq-w4a16-g128-n256-s2048

Qwen3-4B-Thinking-2507-llmc-gptq-w4a16-g128-n256-s2048

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
• —calibration samples: 256
• —max sequence length: 2048