dahara1/gemma-2-2b-jpn-it-gguf-japanese-imatrix
Quantization vs google/gemma-2-2b-jpn-it. dahara1/gemma-2-2b-jpn-it-gguf-japanese-imatrix is a GGUF quantization (F16) of the same weights: 106 tensors match exactly and 182 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/105, MLP 0/78, Attention 0/104