mlx-community/HiDream-O1-Image-Dev-mlx-bf16
Same weights, converted vs HiDream-ai/HiDream-O1-Image-Dev. Same weights stored in another dtype (F32 → BF16), plus 351 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/144, Attention 0/144, MLP 0/108
Same weights, converted vs HiDream-ai/HiDream-O1-Image-Dev. Same weights stored in another dtype (F32 → BF16), plus 351 new tensors.
Tensors changed: Embeddings 0/1, Norms 0/144, Attention 0/144, MLP 0/108