Image models · MiniMax

MiniMax H3 Image New

Name: MiniMax H3 Image
Author: MiniMax

Backbone: 33.1B
Native output: 2048×2048
Default steps: 6
License: minimax-h3-image-community
Released: 2026-11

How to run it

Original weights · Hugging Face

Full-precision files from MiniMax, for fine-tuning, vLLM, Transformers, Diffusers or ComfyUI.

huggingface.co/MiniMaxAI/MiniMax-H3-Image (opens in a new tab)

No sign-in needed.

Official repo · GitHub

Reference code, inference scripts and docs from MiniMax. The weights themselves download from Hugging Face.

github.com/MiniMax-AI/MiniMax-H3-Image (opens in a new tab)

git clone https://github.com/MiniMax-AI/MiniMax-H3-Image

Links checked 2 hours ago against Hugging Face, Ollama and GitHub.

Apps that run MiniMax H3 Image

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`	138 GB	71.7 GB	27.5 GB	Original weights (opens in a new tab)
`FP8`	72.0 GB	38.6 GB	16.0 GB	Original weights (opens in a new tab)

Components

Backbone: 33.1B
VAE: 0.584B
Qwen3-VL 32B: 33.36B

Best hardware for MiniMax H3 Image

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
91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 96/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA RTX PRO 6000 Blackwell	`FP8`	72.0 GB / 96.0 GB	6.6 s	Runs great
91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 92/100 (quality, fit, speed and memory use) sets the ranking.	AMD Ryzen AI Max+ 395 (128 GB)	`FP8`	72.0 GB / 96.0 GB	17 s	Runs well
91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA RTX Spark N1X (6144-core GPU) (128 GB)	`FP8`	72.0 GB / 102 GB	20 s	Runs well
91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 91/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GB10 (128 GB)	`FP8`	72.0 GB / 115 GB	19 s	Runs well
91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 85/100 (quality, fit, speed and memory use) sets the ranking.	Apple M2 Ultra (192 GB)	`FP8`	72.0 GB / 144 GB	39 s	Runs well
91Excellent quality (A+) · 91 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.	Apple M3 Ultra (256 GB)	`FP8`	72.0 GB / 192 GB	38 s	Runs well
91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 4090	`FP8`	16.0 GB / 24.0 GB	12 s	Runs greatCPU offload
91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 81/100 (quality, fit, speed and memory use) sets the ranking.	AMD Radeon RX 7900 XTX	`FP8`	16.0 GB / 24.0 GB	13 s	Runs greatCPU offload
91Excellent quality (A+) · 91 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 5090	`FP8`	16.0 GB / 32.0 GB	9.8 s	Runs greatCPU offload
91Excellent quality (A+) · 91 of 100: how capable the model is at FP8, whatever it runs on. Match score 78/100 (quality, fit, speed and memory use) sets the ranking.	NVIDIA GeForce RTX 3090	`FP8`	16.0 GB / 24.0 GB	22 s	Runs wellCPU offload

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.