mmnga/gemma-3-270m-it-gguf
Quantization vs google/gemma-3-270m-it. mmnga/gemma-3-270m-it-gguf is a GGUF quantization (Q8_0) of the same weights: 109 tensors match exactly and 127 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/109, MLP 0/54, Attention 0/72