AnalysisAI ModelsAugust 5, 2026

Pruned Qwen3-VL 32B GGUF released, starts at 6.7GB

Community GGUF of a pruned Qwen3-VL 32B, with unused text-encoder parts removed for smaller size. Weights start at 6.7GB; requires the author's fork of City96's GGUF loader.

1 source

Daily brief

Get tomorrow's AI brief in your inbox

More stories today

Open the live feed