mlx-community/Qwen3.8-27B-MTP-bf16
Partial fine-tune (fewer layers) vs Qwen/Qwen3.8-27B. mlx-community/Qwen3.8-27B-MTP-bf16 matches part of Qwen/Qwen3.8-27B (15 of its 1199 tensors; the rest of Qwen/Qwen3.8-27B has no counterpart). On the shared part: Partial change: 0% of the weights changed (embeddings, norms), in 1 of 1 layers.
Tensors changed: other 0/1, Norms 6/6, MLP 0/3, Attention 0/4, Embeddings 1/1
1 derivatives checked
- t0rr3sp3dr0/Qwen3.8-27B-MLX-MTP-bf16: Partial fine-tune (fewer layers)
6 other repos hold byte-for-byte identical weight files.