Phil2Sat

/

Qwen-Image-Edit-Rapid-AIO-GGUF

like 203

Hi @Phil2Sat and everyone,

First off, thank you so much for your continued work on the GGUF for Qwen-Image-Edit-Rapid-AIO! It is a fantastic project.

I noticed that the GGUF versions currently available in the repository are for v9. Would it be possible for you to upload GGUF builds for the new v16 version (https://huggingface.co/Phr00t/Qwen-Image-Edit-Rapid-AIO/tree/main/v16)? I am very eager to test out the latest improvements in that format.

If you are too busy to generate them yourself, could you (or anyone in the community) perhaps guide me on the correct process to generate them? I tried to quantize v16 using llama.cpp locally, but the process failed to complete; it consistently freezes when processing the last few layers.

Any assistance or updates would be greatly appreciated. Thanks again for your time and hard work!

Best regards,

Tom