---
license: apache-2.0
base_model:
- Qwen/Qwen3-Coder-30B-A3B-Instruct
library_name: transformers
---

This is my (first) attempt at quantizing this Qwen3 model (Qwen/Qwen3-Coder-30B-A3B-Instruct) using auto-round, like so:

```
auto-round-light --model "Qwen/Qwen3-Coder-30B-A3B-Instruct" --scheme "W4A16" --format "auto_gptq" --output_dir "./Quantized" --model_dtype fp16
```