mlx-community/Ministral-3-14B-Reasoning-2512-bf16

Full fine-tune vs mistralai/Ministral-3-14B-Base-2512. Fine-tune: 100% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 1/1, Norms 74/82, MLP 120/120, Attention 160/160, other 3/3, lm_head 1/1

On the Hub · Downloads on Model Pulse