---
license: apache-2.0
base_model:
- Qwen/Qwen3-4B-Instruct-2507
library_name: transformers
---

This is my (first) attempt at quantizing this Qwen3 model (Qwen/Qwen3-4B-Instruct-2507) using auto-round, like so:

```bash
auto-round --model "Qwen/Qwen3-4B-Instruct-2507" --scheme "W4A16" --format "auto_gptq" --output_dir "./Quantized" --model_dtype fp16
```
The primary purpose of these quants are to make them run on consumer AMD GPUs, which they do work, in my case.