Interesting post, but the last bit of logic pointing to the Neural Engine for ML...

light | darkhn

		docfort 14 days ago \| parent \| context \| \| on: My iPhone 16 Pro Max produces garbage output when ... Interesting post, but the last bit of logic pointing to the Neural Engine for MLX doesn’t hold up. MLX supports running on CPU, Apple GPU via Metal, and NVIDIA GPU via CUDA: https://github.com/ml-explore/mlx/tree/main/mlx/backend