bartowski/gemma-2-9b-it-GGUF
Quantization vs google/gemma-2-9b-it. bartowski/gemma-2-9b-it-GGUF is a GGUF quantization (F16) of the same weights: 170 tensors match exactly and 294 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/169, MLP 0/126, Attention 0/168