tanishqpatil/gemma-e4b-thinking
Not comparable yet vs google/gemma-2b. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 164/648 match), usually an architecture llama.cpp's name map doesn't cover yet.
Not comparable yet vs google/gemma-2b. Not verifiable yet: the GGUF's tensors don't map onto the other model's names (0 of 164/648 match), usually an architecture llama.cpp's name map doesn't cover yet.