mlabonne/gemma-3-4b-it-qat-abliterated-GGUF
Quantization (fewer layers) vs google/gemma-3-4b-it-qat-q4_0-unquantized. mlabonne/gemma-3-4b-it-qat-abliterated-GGUF matches part of google/gemma-3-4b-it-qat-q4_0-unquantized (444 of its 883 tensors; the rest of google/gemma-3-4b-it-qat-q4_0-unquantized has no counterpart). On the shared part: mlabonne/gemma-3-4b-it-qat-abliterated-GGUF is a GGUF quantization (Q8_0) of the same weights: 205 tensors match exactly and 239 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/205, MLP 0/102, Attention 0/136