dahara1/gemma-3-27b-it-qat-japanese-imatrix
Quantization (fewer layers) vs google/gemma-3-27b-it-qat-q4_0-unquantized. dahara1/gemma-3-27b-it-qat-japanese-imatrix matches part of google/gemma-3-27b-it-qat-q4_0-unquantized (808 of its 1247 tensors; the rest of google/gemma-3-27b-it-qat-q4_0-unquantized has no counterpart). On the shared part: dahara1/gemma-3-27b-it-qat-japanese-imatrix is a GGUF quantization (F16) of the same weights: 374 tensors match exactly and 434 within quantization error.
Tensors changed: Embeddings 0/1, Norms 0/373, MLP 0/186, Attention 0/248