README.md

metadata

base_model: Qwen/Qwen3-Coder-30B-A3B-Instruct
library_name: transformers
license_link: https://huggingface.co/Qwen/Qwen3-Coder-30B-A3B-Instruct/blob/main/LICENSE
license: apache-2.0
tags:
  - qwen3
  - qwen
  - gptq
  - 4 Bit

4-bit Quantization of the Qwen3 30B A3B Thinking 2507 Model

Quantized using GPTQModel

quantiziation config:

quant_config = QuantizeConfig(
    bits=4,
    group_size=32,
    sym=True,
    desc_act=False,
    true_sequential=True,
    pack_dtype=torch.int32,
    damp_percent=0.1       
)