Qwen3-0.6B-exl3 / README.md
turboderp's picture
Update README.md
ae608a6 verified
---
license: apache-2.0
base_model: Qwen/Qwen3-0.6B
base_model_relation: quantized
quantized_by: turboderp
tags:
- exl3
---
EXL3 quants of [Qwen3-0.6B](https://huggingface.co/Qwen/Qwen3-0.6B)
[2.75 bits per weight / H5](https://huggingface.co/turboderp/Qwen3-0.6B-exl3/tree/2.75bpw_H5) *
[3.00 bits per weight](https://huggingface.co/turboderp/Qwen3-0.6B-exl3/tree/3.0bpw) *
[3.50 bits per weight](https://huggingface.co/turboderp/Qwen3-0.6B-exl3/tree/3.5bpw)
[4.00 bits per weight](https://huggingface.co/turboderp/Qwen3-0.6B-exl3/tree/4.0bpw)
[5.00 bits per weight](https://huggingface.co/turboderp/Qwen3-0.6B-exl3/tree/5.0bpw)
[6.00 bits per weight](https://huggingface.co/turboderp/Qwen3-0.6B-exl3/tree/6.0bpw)
[8.00 bits per weight / H8](https://huggingface.co/turboderp/Qwen3-0.6B-exl3/tree/8.0bpw_H8)
*) Reasoning seems unstable below 3.5 bpw
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6383dc174c48969dcf1b4fce/UQ9YuDyEPFMfBb2beXcS8.png)