MiniMax H3 (Hailuo)
Open weights of MiniMax's Hailuo video model. A large 33B model that makes video from text and images, but needs several server GPUs.
- Developer
- MiniMax, China
- First release
- Jul 2026
- Latest release
- Jul 2026
- Sizes
- 33B + 32B encoder
- License
- Commercial use with conditionsMiniMax H3 Community License — own license with conditions
- Running
- On your own serverNeeds a GPU
- Industries
- Media and production, Marketing and content
What it does
- Cinematic ad videos
- Video from text and images
- Complex scenes with motion
Where it is used
Hardware requirements
Versions
- MiniMax-H3
How to run it
I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.
Frequently asked questions
Can MiniMax H3 (Hailuo) be used in a commercial project?
With conditions. License: MiniMax H3 Community License — own license with conditions. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.
What hardware does MiniMax H3 (Hailuo) need?
At minimum: Server with several GPUs — flagship versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.
Does MiniMax H3 (Hailuo) support Russian?
Language does not matter for this model: it does not work with text.
Where can I download MiniMax H3 (Hailuo) and what does it cost?
The MiniMax H3 (Hailuo) weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.
How I deploy it for clients
- SelectionI pick the model size for your task and hardware and test it on your examples.
- DeploymentI deploy it on your server or in a closed network and provide an API.
- Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
- IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.
Similar models
Text-to-video and image-to-video; the small version runs on a gaming GPU. After 2.2 only applied models are open: editing (VACE), audio-driven talking characters (S2V), dancing to music (Dancer).
DetailsVideoLTX-Video / LTX-2Lightricks · IsraelCommercial use with conditionsA fast video model; with LTX-2 it generates video with sound and speech in one go. Camera and pose control, lightweight versions available.
DetailsVideoMAGISand AI · ChinaCommercial use allowedVideo generated chunk by chunk in sequence, so a clip can be extended indefinitely. MAGI-2 produces video with sound.
DetailsSource: huggingface.co/MiniMaxAI/MiniMax-H3. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


