mlx-community/VibeThinker-3B

Same weights, repacked vs WeiboAI/VibeThinker-3B. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/1, Norms 0/73, MLP 0/108, Attention 0/252

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

On the Hub · Downloads on Model Pulse