mlx-community/gemma-4-26B-A4B-it-OptiQ-4bit-REAP-14B

Same weights, repacked vs mlx-community/gemma-4-26B-A4B-it-OptiQ-4bit. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/6, Norms 0/433, other 0/62, MLP 0/351, Attention 0/453

On the Hub · Downloads on Model Pulse