FadedRedStar/gemma-4-E4B-it-qat-q4_0-heretic-GGUF
Not comparable yet vs coder3101/gemma-4-E4B-it-qat-q4_0-unquantized-heretic. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (3 of 2076/49 match), usually an architecture llama.cpp's name map doesn't cover yet.