mradermacher/gemma-3-27b-pt-GGUF
Quantization (fewer layers) vs google/gemma-3-27b-pt. mradermacher/gemma-3-27b-pt-GGUF matches part of google/gemma-3-27b-pt (807 of its 1247 tensors; the rest of google/gemma-3-27b-pt has no counterpart). On the shared part: mradermacher/gemma-3-27b-pt-GGUF is a GGUF quantization (Q8_0) of the same weights: 373 tensors match exactly and 434 within quantization error.
Tensors changed: Norms 0/373, MLP 0/186, Attention 0/248