bluehawana/Qwen3.8-27B-bf16-MTP-MLX
Same weights, repacked vs mlx-community/Qwen3.8-27B-bf16. Same weights in different files (re-saved, re-sharded or new metadata), plus 15 new tensors.
Tensors changed: Embeddings 0/4, Norms 0/319, Attention 0/556, MLP 0/304, lm_head 0/1