# Modifications

Modified by ixim / iximbox for Image21-MLX: converted from the pinned BF16 source to MLX layout; eligible linear weights use groupwise affine quantization. See conversion.json for precision and exceptions. Built with Qwen.

VAE convolution layout is transposed without reducing FP32 precision. The entire vision tower, token embeddings, language head, norms, transformer input/output projections, timestep embedding and modulation remain floating point.