mlx-community/Apertus-8B-Instruct-2509-bf16

Same weights, repacked vs swiss-ai/Apertus-8B-Instruct-2509. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/1, Norms 0/129, MLP 0/192, Attention 0/128, lm_head 0/1

On the Hub · Downloads on Model Pulse