lmstudio-community/gemma-3-12B-it-qat-GGUF
Full fine-tune (fewer layers) vs google/gemma-3-12b-it. lmstudio-community/gemma-3-12B-it-qat-GGUF matches part of google/gemma-3-12b-it (626 of its 1065 tensors; the rest of google/gemma-3-12b-it has no counterpart). On the shared part: lmstudio-community/gemma-3-12B-it-qat-GGUF is a GGUF (Q4_0) of different weights. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 177/289, MLP 144/144, Attention 192/192