---
library_name: exllamav3
license: apache-2.0
license_link: https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct/blob/main/LICENSE
pipeline_tag: text-generation
base_model: Qwen/Qwen3-Coder-480B-A35B-Instruct
base_model_relation: quantized
tags:
  - exl3
---

Exllamav3 quantization of [Qwen/Qwen3-Coder-480B-A35B-Instruct](https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct)

[2.00 bpw h6](https://huggingface.co/MikeRoz/Qwen3-Coder-480B-A35B-Instruct-exl3/tree/2.00bpw_H6) 114.396 GiB      
[3.00 bpw h6](https://huggingface.co/MikeRoz/Qwen3-Coder-480B-A35B-Instruct-exl3/tree/2.00bpw_H6) 170.069 GiB      

The 2.00bpw quant will fit in six 24 GB cards with 40k of fp16 context.