mradermacher/gemma-3-12b-it-qat-int4-unquantized-heretic-GGUF
Quantization (fewer layers) vs megabytes/gemma-3-12b-qat-int4-heretic. mradermacher/gemma-3-12b-it-qat-int4-unquantized-heretic-GGUF matches part of megabytes/gemma-3-12b-qat-int4-heretic (626 of its 1065 tensors; the rest of megabytes/gemma-3-12b-qat-int4-heretic has no counterpart). On the shared part: mradermacher/gemma-3-12b-it-qat-int4-unquantized-heretic-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