unsloth/gemma-4-12B-it-qat-q4_0-unquantized
Full fine-tune vs google/gemma-4-12B-it. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 5/12, Norms 193/289, other 46/48, MLP 144/144, Attention 184/184
2 derivatives checked
- efficiencyx/Jun-LoRA-12B-GGUF: Full fine-tune
- efficiencyx/Jun-LoRA-12B-v5-GGUF: Full fine-tune
7 other repos hold byte-for-byte identical weight files.