t0rr3sp3dr0/Qwen3.8-27B-MLX-MTP-8bit
Partial fine-tune (fewer layers) vs mlx-community/Qwen3.8-27B-MTP-8bit. mlx-community/Qwen3.8-27B-MTP-8bit matches part of t0rr3sp3dr0/Qwen3.8-27B-MLX-MTP-8bit (28 of its 2207 tensors; the rest of t0rr3sp3dr0/Qwen3.8-27B-MLX-MTP-8bit has no counterpart). On the shared part: Partial change: 0% of the weights changed (embeddings, norms), in 1 of 1 layers.
Tensors changed: Norms 6/6, MLP 0/9, Attention 0/12, Embeddings 1/1