Quantizing model

[yachty66]

I want to make the model smaller by quantizing it. I found a resource where they quantized Flux Fill Dev: https://huggingface.co/YarvixPA/FLUX.1-Fill-dev-gguf

Can I use the quantization method for your fine-tune as well, or is the model structure of your fine-tune different and therefore wouldn't work?

[nftblackmagic]

I am not sure about this part. You can definitely try it.