WhiskyAKM/Gemma-4-26B-A4B-it-qat-NVFP4-GGUF
Not comparable yet vs google/gemma-4-26B-A4B-it. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (3 of 1013/49 match), usually an architecture llama.cpp's name map doesn't cover yet.