grimjim/gemma-3-12b-it-abliterated-GGUF
Quantization (fewer layers) vs grimjim/gemma-3-12b-it-abliterated. grimjim/gemma-3-12b-it-abliterated-GGUF matches part of grimjim/gemma-3-12b-it-abliterated (626 of its 1065 tensors; the rest of grimjim/gemma-3-12b-it-abliterated has no counterpart). On the shared part: grimjim/gemma-3-12b-it-abliterated-GGUF is a GGUF quantization (Q8_0) of the same weights: 289 tensors match exactly and 337 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/289, MLP 0/144, Attention 0/192