view reply If you wanna take a Qwen 3.6 look at this model - https://huggingface.co/LuffyTheFox/Qwen3.6-35B-A3B-Plus-Uncensored-Wasserstein-GGUF Only this was fixed with layers problem on qwen
APEX Quants (GGUF) Collection MoE models quantized with the APEX Quantization technique ( https://github.com/mudler/apex-quant ) • 27 items • Updated 9 days ago • 88
aifeifei798/Gemma-4-31B-Cognitive-Unshackled Image-Text-to-Text • 31B • Updated 29 days ago • 92.6k • 21