DevQuasar/google.gemma-4-12B-it-GGUF

Full fine-tune vs google/gemma-4-12B-it. DevQuasar/google.gemma-4-12B-it-GGUF is a GGUF (Q2_K) of different weights. Fine-tune: 100% of the weights changed, across 48 of 48 layers.

Tensors changed: Embeddings 1/1, Norms 260/289, MLP 144/144, Attention 184/184

On the Hub · Downloads on Model Pulse