Image models · Ant Group (inclusionAI)

Ming-Image 0.1 Design

Name: Ming-Image 0.1 Design
Author: Ant Group (inclusionAI)

Backbone: 6.2B
Native output: 2048×2048
Default steps: 12
License: mit
Released: 2026-09

How to run it

Original weights · Hugging Face

Full-precision files from Ant Group (inclusionAI), for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/inclusionAI/Ming-Image-0.1-Design (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from Ant Group (inclusionAI). The weights themselves download from Hugging Face.

github.com/inclusionAI/Ming-Image (opens in a new tab)

Official inference code (infer.py) for text-to-image and transparent RGBA output; the model card also recommends vLLM-Omni for serving.

git clone https://github.com/inclusionAI/Ming-Image

Links checked 5 days ago against Hugging Face, Ollama and GitHub.

Apps that run Ming-Image 0.1 Design

Our pick for each kind of computer, assuming the model fits in its memory. Pick your own GPU or device in the Model Finder for an exact answer.

Mac (Apple silicon)

ComfyUI

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Also good:

Windows PC, NVIDIA GPU

ComfyUI

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Also good:

Linux, NVIDIA or AMD GPU

ComfyUI

Runs this model with built-in or popular custom nodes; GGUF files load with ComfyUI-GGUF.

Also good:

App	Type	Opens it as	Systems	Engine	Start
ComfyUI	Desktop app	Built-in support	macOSWindowsLinux	PyTorch, GGUF via ComfyUI-GGUF	Get ComfyUI
SwarmUI	Desktop app	Built-in support	macOSWindowsLinux	ComfyUI	Get SwarmUI
SD.Next	Desktop app	Built-in support	macOSWindowsLinux	PyTorch	Get SD.Next
Stability Matrix	Desktop app	Built-in support	macOSWindowsLinux	installs ComfyUI, Forge, InvokeAI, SwarmUI, SD.Next or Fooocus	Get Stability Matrix

Which apps can open a model depends on the files published for it: GGUF for llama.cpp-based apps, MLX for Apple’s engine, the original weights for vLLM and SGLang. Compare every app.

Memory needed

Peak GPU memory at the native output size. Offloading moves the text encoder, or the whole pipeline, to system RAM between steps.

Precision	Everything on GPU	Text encoder offloaded	Sequential offload	Download
`FP16`	63.9 GB	26.8 GB	18.5 GB	Original weights (opens in a new tab)
`FP8`	39.2 GB	20.6 GB	16.4 GB	Original weights (opens in a new tab)

Components

Backbone: 6.15B
VAE: 0.127B
Ming VLM 17B (Ling-mini-2.0 MoE + Qwen2.5-VL vision): 17B
Qwen2 1.5B connector: 1.54B

Best hardware for Ming-Image 0.1 Design

The least expensive GPU in our catalog that runs it without offloading is the AMD Radeon RX 7900 XT (launch price $899) at FP8.

Quality	Hardware	Quant	Memory	Speed	Runs
86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA RTX PRO 6000 Blackwell	`FP16`	63.9 GB / 96.0 GB	12 s	Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 87/100 (quality, fit, speed and memory use) sets the ranking.	AMD Ryzen AI Max+ 395 (128 GB)	`FP16`	63.9 GB / 96.0 GB	31 s	Runs well
86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 5090	`FP16`	26.8 GB / 32.0 GB	14 s	Runs wellencoder in RAM
86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 86/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA RTX Spark N1X (6144-core GPU) (128 GB)	`FP16`	63.9 GB / 102 GB	36 s	Runs well
86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 84/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GB10 (128 GB)	`FP16`	63.9 GB / 115 GB	34 s	Runs well
84Great quality (A) · 84 of 100: how capable the model is at FP8, whatever it runs on. Match score 83/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4090	`FP8`	20.6 GB / 24.0 GB	15 s	Runs welltight fit · encoder in RAM
84Great quality (A) · 84 of 100: how capable the model is at FP8, whatever it runs on. Match score 82/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 7900 XTX	`FP8`	20.6 GB / 24.0 GB	17 s	Runs welltight fit · encoder in RAM
84Great quality (A) · 84 of 100: how capable the model is at FP8, whatever it runs on. Match score 79/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 3090	`FP8`	20.6 GB / 24.0 GB	29 s	Runs welltight fit · encoder in RAM
86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GH200 Grace Hopper (96 GB GPU)	`FP16`	63.9 GB / 96.0 GB	11 s	Runs great
86Excellent quality (A+) · 86 of 100: how capable the model is at FP16, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA H100 80GB SXM	`FP16`	63.9 GB / 80.0 GB	11 s	Runs great

Check it on your own hardware

Estimates come from published hardware specs and our open formulas, not from running the model on your machine. Real speed varies with runtime, drivers and settings. Numbers marked “Measured” come from a linked benchmark.