MassivDash/Gemma-4-Rust-Coder
Not comparable yet vs google/gemma-4-E4B-it. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (51 of 2130/601 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs google/gemma-4-E4B-it. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (51 of 2130/601 match), usually an architecture llama.cpp's name map doesn't cover yet.