turboderp's picture
Update README.md
348d18d verified
|
Raw
History Blame Contribute Delete
1.63 kB
---
license: apache-2.0
base_model: Qwen/Qwen3-Next-80B-A3B-Instruct
base_model_relation: quantized
quantized_by: turboderp
tags:
- exl3
---
EXL3 quants of [Qwen3-Next-80B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct)
⚠️ Requires ExLlamaV3 v0.0.7 (or v0.0.6 `dev` branch)
Base bitrates:
[2.00 bits per weight](https://huggingface.co/turboderp/Qwen3-Next-80B-A3B-Instruct-exl3/tree/2.0bpw)
[3.00 bits per weight](https://huggingface.co/turboderp/Qwen3-Next-80B-A3B-Instruct-exl3/tree/3.0bpw)
[4.00 bits per weight](https://huggingface.co/turboderp/Qwen3-Next-80B-A3B-Instruct-exl3/tree/4.0bpw)
[5.00 bits per weight](https://huggingface.co/turboderp/Qwen3-Next-80B-A3B-Instruct-exl3/tree/5.0bpw)
Optimized:
[2.08 bits per weight](https://huggingface.co/turboderp/Qwen3-Next-80B-A3B-Instruct-exl3/tree/2.08bpw)
[2.27 bits per weight](https://huggingface.co/turboderp/Qwen3-Next-80B-A3B-Instruct-exl3/tree/2.27bpw)
[2.78 bits per weight](https://huggingface.co/turboderp/Qwen3-Next-80B-A3B-Instruct-exl3/tree/2.78bpw)
[3.14 bits per weight](https://huggingface.co/turboderp/Qwen3-Next-80B-A3B-Instruct-exl3/tree/3.14bpw)
[3.53 bits per weight](https://huggingface.co/turboderp/Qwen3-Next-80B-A3B-Instruct-exl3/tree/3.53bpw)
[4.06 bits per weight](https://huggingface.co/turboderp/Qwen3-Next-80B-A3B-Instruct-exl3/tree/4.06bpw)
[4.51 bits per weight](https://huggingface.co/turboderp/Qwen3-Next-80B-A3B-Instruct-exl3/tree/4.51bpw)
![image/png](https://cdn-uploads.huggingface.co/production/uploads/6383dc174c48969dcf1b4fce/o102Nhe2xdm7WzgMlg1tg.png)