mlx-community/Qwen3-0.6B-bf16

Same weights, repacked vs Qwen/Qwen3-0.6B. Same weights in different files (re-saved, re-sharded or new metadata).

Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112

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

On the Hub · Downloads on Model Pulse