exllamav3 quantizations of Qwen/Qwen3.5-397B-A17B. Quantized using commit 144d826 of the dev branch (version was bumped to v0.2.23 in the next commit).

Optimized

2.08bpw_h6 99.272 GiB

Straight

2.00bpw_h6 96.614 GiB

Deleted the 3, 4 and 5bpw quants to save space. Another user has uploaded these here: https://huggingface.co/NeuroSenko/Qwen3.5-397B-A17B-exl3

Matplotlib Catbench

2.00bpw 2.08bpw

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

Image-Text-to-Text

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for MikeRoz/Qwen3.5-397B-A17B-exl3

Base model

Qwen/Qwen3.5-397B-A17B

Quantized

(73)

this model