---
license: apache-2.0
---
EXL2 quants of [Qwen2-VL-72B-Instruct](https://huggingface.co/Qwen/Qwen2-VL-72B-Instruct)

[4.00 bits per weight](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/tree/4.0bpw)    
[4.50 bits per weight](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/tree/4.5bpw)    
[5.00 bits per weight](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/tree/5.0bpw)    
[6.00 bits per weight](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/tree/6.0bpw)    

(2.3bpw to 3.5bpw revisions are in also this repo, but they are unstable. Working on it.)

[measurement.json](https://huggingface.co/turboderp/Qwen2-VL-72B-Instruct-exl2/blob/main/measurement.json)