mradermacher/Lightricks-gemma-3-12b-it-qat-q4_0-unquantized-GGUF
Quantization (fewer layers) vs ibyteohdear/Lightricks-gemma-3-12b-it-qat-q4_0-unquantized. mradermacher/Lightricks-gemma-3-12b-it-qat-q4_0-unquantized-GGUF matches part of ibyteohdear/Lightricks-gemma-3-12b-it-qat-q4_0-unquantized (626 of its 1065 tensors; the rest of ibyteohdear/Lightricks-gemma-3-12b-it-qat-q4_0-unquantized has no counterpart). On the shared part: mradermacher/Lightricks-gemma-3-12b-it-qat-q4_0-unquantized-GGUF is a GGUF quantization (Q4_K_M) 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