rahul7star/gemma-gguf
Not comparable yet vs google/gemma-4-12B-it. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (14 of 677/441 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs google/gemma-4-12B-it. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (14 of 677/441 match), usually an architecture llama.cpp's name map doesn't cover yet.