turboderp
/

Qwen3-VL-235B-A22B-Thinking-exl3

Model card Files Files and versions

EXL3 quants of Qwen3-VL-235B-A22B-Thinking

Base bitrates:

2.00 bits per weight
3.00 bits per weight
4.00 bits per weight

Optimized:

2.07 bits per weight
2.29 bits per weight
2.54 bits per weight
3.05 bits per weight
3.51 bits per weight

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

Inference Providers NEW

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

Model tree for turboderp/Qwen3-VL-235B-A22B-Thinking-exl3

Base model

Qwen/Qwen3-VL-235B-A22B-Thinking

Quantized

(17)

this model

Collection including turboderp/Qwen3-VL-235B-A22B-Thinking-exl3

EXL3 models

42 items • Updated about 8 hours ago • 37