---
base_model: Qwen/Qwen3-30B-A3B
library_name: transformers
license_link: https://huggingface.co/Qwen/Qwen3-30B-A3B/blob/main/LICENSE
license: apache-2.0
tags:
- qwen3
- qwen
- gptq
- 8bit
---

# 8-bit Quantization of the Qwen3 30B A3B Model
Quantized using GPTQModel

quantiziation config:
```
quant_config = QuantizeConfig(
    bits=8,
    group_size=32,
    sym=True,
    desc_act=False,
    true_sequential=True,
    pack_dtype=torch.int32,
    damp_percent=0.1       
)
```