mlx-community/Ministral-3-3B-Instruct-2512-bf16

Full fine-tune vs mistralai/Ministral-3-3B-Base-2512. Fine-tune: 100% of the weights changed, across 26 of 26 layers.

Tensors changed: Embeddings 1/1, Norms 43/54, MLP 78/78, Attention 104/104, other 2/3

On the Hub · Downloads on Model Pulse