dgflash/FLUX.1-dev-4bit-gguf
Not comparable yet vs black-forest-labs/FLUX.1-dev. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 244/780 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs black-forest-labs/FLUX.1-dev. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 244/780 match), usually an architecture llama.cpp's name map doesn't cover yet.