DavidAU/Gemma-3-12b-it-MAX-HORROR-Imatrix-GGUF
Quantization (fewer layers) vs google/gemma-3-12b-it. DavidAU/Gemma-3-12b-it-MAX-HORROR-Imatrix-GGUF matches part of google/gemma-3-12b-it (625 of its 1065 tensors; the rest of google/gemma-3-12b-it has no counterpart). On the shared part: DavidAU/Gemma-3-12b-it-MAX-HORROR-Imatrix-GGUF is a GGUF quantization (Q8_0/BF16) of the same weights: 289 tensors match exactly and 336 within quantization error.
Tensors changed: Norms 0/289, MLP 0/144, Attention 0/192