mradermacher/gemma-2-27b-GGUF
Quantization vs google/gemma-2-27b. mradermacher/gemma-2-27b-GGUF is a GGUF quantization (Q8_0) of the same weights: 185 tensors match exactly and 323 within quantization error.
Tensors changed: Embeddings 0/1, Attention 0/184, Norms 0/185, MLP 0/138