mlx-community/Qwen3.5-9B-bf16

Full fine-tune vs Qwen/Qwen3.5-9B-Base. Fine-tune: 100% of the weights changed, across 32 of 32 layers.

Tensors changed: Embeddings 1/1, MLP 96/96, Attention 173/200, Norms 105/105

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

On the Hub · Downloads on Model Pulse