praiselab-picuslab/Voxtral-Mini-4B-Realtime-2602-GGUF

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

Tensors changed: Norms 53/53, MLP 78/78, Attention 104/104

4 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse