mlx-community/Qwen3-Coder-Next-bf16
Partial fine-tune vs Qwen/Qwen3-Coder-Next. Partial change: 0% of the weights changed (norms), in 48 of 48 layers.
Tensors changed: Embeddings 0/1, Norms 121/157, Attention 0/228, MLP 0/240, lm_head 0/1
Partial fine-tune vs Qwen/Qwen3-Coder-Next. Partial change: 0% of the weights changed (norms), in 48 of 48 layers.
Tensors changed: Embeddings 0/1, Norms 121/157, Attention 0/228, MLP 0/240, lm_head 0/1