RoboticsVideo

NVIDIA Cosmos

"World" models for robots and self-driving vehicles: they generate realistic video of physical scenes and predict actions. Cosmos 3 combines understanding, generation and control.

Developer
NVIDIA, USA
First release
Jan 2025
Latest release
Jul 2026
Sizes
2B – 65B
License
Commercial use allowedCosmos 3: OpenMDW 1.1 (permissive, commercial use allowed); earlier versions: NVIDIA Open Model License, commercial use also allowed
Running
On your own serverNeeds a GPU
Industries
Manufacturing and logistics, Science and research, Media and production
Deploy on your server Hugging Face GitHub

What it does

  • Synthetic video for training robots and self-driving vehicles
  • Testing scenarios in simulation
  • Robot control (Policy versions)

Where it is used

RoboticsAutonomous transportManufacturing and warehouses

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
no versions
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
fits

Versions

  1. Cosmos 3 Edge
  2. Cosmos 3 (Nano, Super)
  3. Cosmos-Predict2.5
  4. Cosmos-Predict2
  5. Cosmos 1.0

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

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 NVIDIA Cosmos be used in a commercial project?

Yes. License: Cosmos 3: OpenMDW 1.1 (permissive, commercial use allowed); earlier versions: NVIDIA Open Model License, commercial use also allowed. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does NVIDIA Cosmos need?

At minimum: One GPU with 16–80 GB — mid-size 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 NVIDIA Cosmos support Russian?

Language does not matter for this model: it does not work with text.

Where can I download NVIDIA Cosmos and what does it cost?

The NVIDIA Cosmos 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

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

RoboticsNVIDIA Isaac GR00TNVIDIA · USACommercial use with conditions

NVIDIA's foundation model for humanoid robots and robot arms: it sees, understands a command and outputs movements. Built into the Isaac ecosystem.

DetailsVideoWanAlibaba · ChinaCommercial use allowed

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).

Details3DHY-World (HunyuanWorld)Tencent · ChinaCommercial use with conditions

Generates whole 3D worlds and scenes from text or an image that you can walk through. The second version builds a scene from video and photos.

Details

Source: nvidianews.nvidia.com/news/nvidia-launches-cosmos-3-the-open-frontier-. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.