WhiskyAKM/Gemma-4-12B-it-qat-GGUF
Full fine-tune vs google/gemma-4-12B-it. WhiskyAKM/Gemma-4-12B-it-qat-GGUF is a GGUF (BF16) of different weights. Fine-tune: 100% of the weights changed, across 48 of 48 layers.
Tensors changed: Embeddings 1/1, Norms 166/289, MLP 144/144, Attention 184/184
1 derivatives checked
- WhiskyAKM/Gemma-4-12B-it-qat-NVFP4-GGUF: Different architecture