Exl3 5.0bpw h6 quantization of Qwen/Qwen3-235B-A22B using 002bd31 commit of Exllamav3
148.4gb, requires ~160gb with 64k unquantized context.
- Downloads last month
- 3
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support
Model tree for Minthy/Qwen3-235B-A22B-5.0bpw-h6-exl3
Base model
Qwen/Qwen3-235B-A22B