Request Qwen-Image-Pruning GGUF~

#1
by sunnyboxs - opened

Qwen-Image-Pruning is a model made by OPPO after pruning.
The model size is about 30% - 50% smaller than the original, and the effect is almost the same.
Looking forward to uploading the pruning version GGUF~

Model size comparison:
Qwen-Image: 40Gb
Qwen-Image-Pruning: 28Gb

https://huggingface.co/OPPOer/Qwen-Image-Pruning

QuantStack org

Interesting, ill check it out after wan animate (;

Sign up or log in to comment