---
inference: false
base_model: Qwen/Qwen3-Next-80B-A3B-Instruct
base_model_relation: quantized
tags:
- exl3
library_name: exllamav3
pipeline_tag: text-generation
---

Some pointlessly bigger exllamav3 quants of [Qwen3-Next-80B-A3B-Instruct](https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct) to complement [Turboderp's optimized quants](https://huggingface.co/turboderp/Qwen3-Next-80B-A3B-Instruct-exl3).

[6.00bpw_H6](https://huggingface.co/MikeRoz/Qwen3-Next-80B-A3B-Instruct-exl3/tree/6.00bpw_H6) (56.561 GiB)    
[8.00bpw_H8](https://huggingface.co/MikeRoz/Qwen3-Next-80B-A3B-Instruct-exl3/tree/8.00bpw_H8) (75.026 GiB)