mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B

Same weights, repacked vs mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/6, Norms 0/267, Attention 0/900, MLP 0/688, lm_head 0/3

On the Hub · Downloads on Model Pulse