joeynyc/Ming-Image-0.1-Design-mflux-q8-te6

Ming-Image-0.1-Design — MLX (8-bit DiT, 6-bit text encoder)

An MLX conversion of inclusionAI/Ming-Image-0.1-Design for mflux — 21.2 GB in total. Ming-Image is a design-focused text-to-image model (posters, cards, UI, typography) that outputs RGBA images.

Component	Precision	Size
Ling-mini-2.0 MoE text encoder (mllm/)	6-bit (routers, norms, query tokens full precision)	13.0 GB
Qwen2 connector (connector/)	8-bit	1.4 GB
Projection heads (mlp/)	bf16	0.06 GB
DiT (transformer/)	8-bit	6.5 GB
RGBA VAE (vae/)	bf16	0.25 GB

The checkpoint's Qwen2.5 ViT, lm_head and audio router are not used for text-to-image and are not included.

Usage

Requires mflux with Ming-Image support (the ming-image model family; until it is merged upstream, install mflux from the branch that adds it).

mflux-generate-ming \
  --model path/to/this/repo \
  --prompt "A modern tech conference poster titled 'MLX SUMMIT 2026' ..." \
  --width 1024 --height 1024 --seed 42

Defaults follow the official pipeline: 12 steps, guidance 1.0, flow-match Euler with the checkpoint's static shift of 6. PNGs keep the alpha channel (--flatten-alpha for RGB).

Performance

The DiT stage is identical to the 5-bit-text-encoder variant: on a base M4 Mac mini (24 GB) 512² takes ~1 min (9.8 GB peak) and 1024² 4–4.5 min (14.5 GB peak). The text encoder is freed after encoding the prompt.

Fidelity

The MLX implementation was checked stage by stage against tensors dumped from the official PyTorch pipeline: DiT, VAE and connector at cosine similarity ≥ 0.9999, and the text encoder within the official model's own eager-vs-flash-attention spread (this includes reproducing the official pipeline's autocast-bf16 MoE routing exactly). From the same initial noise it reproduces the official images' layout, typography and text; a little more text-encoder precision than the 5-bit variant, still fits 24 GB Macs.

The DiT is deliberately kept at 8 bits: at 4 bits large headline lettering degrades.

License

MIT, as the original model. Credit to inclusionAI for Ming-Image.