rajaschitnis/gemma-4-12b-it-text-only-4bit-mlx

Partial fine-tune vs mlx-community/gemma-4-12B-it-4bit. Partial change: 11% of the weights changed (mlp), in 48 of 48 layers.

Tensors changed: Embeddings 0/3, Norms 0/289, other 0/48, MLP 144/288, Attention 0/552

On the Hub · Downloads on Model Pulse