NVIDIA

Cosmos3 NIM

Container

NVIDIA

Cosmos3 NIM

Cosmos3 NIM packages the reasoning and generation capabilities of the Cosmos3 World Foundation Model (WFM) into a single container.

Cosmos3 Container Overview

Description:

This container houses Cosmos3 model family. It is a suite of omnimodal world models designed to jointly process and generate language, images, video, audio, and action sequences within a unified Mixture-of-Transformers architecture. By supporting highly flexible input-output configurations, it seamlessly unifies critical modalities for Physical AI — effectively subsuming vision-language models, video generators, world simulators, and world-action models into a single framework.

The container components are ready for commercial or non-commercial use.

License/Terms of Use:

GOVERNING TERMS: Use of this NIM is governed by the NVIDIA Software License Agreement and the Product-Specific Terms for NVIDIA AI Products and Use of the model(s) is governed by the Linux Foundation’s OpenMDW 1.1 license

You are responsible for ensuring that your use of NVIDIA AI Foundation Models complies with all applicable laws.

Deployment Geography:

Global

Release Date:

Hugging Face 05/31/2026 via https://huggingface.co/collections/nvidia/cosmos3
GitHub 05/31/2026 via https://github.com/nvidia/cosmos

Program Classes:

The Cosmos3 Unified Container includes the following models:

Model Name & Link	Use Case	How to Pull the Model
Cosmos3-Nano	For multimodal understanding, world simulation, future prediction, action reasoning, and Physical AI applications.	[Automatic]
Cosmos3-Super	For multimodal understanding, world simulation, future prediction, action reasoning, and Physical AI applications.]	[Automatic]
Cosmos3-Super-Text2Image	Given text input, generate high-fidelity images that are consistent with the provided description]	[Automatic]
Cosmos3-Super-Image2Video	Given one input image and text instructions, generate temporally coherent video sequences that are consistent with the provided visual content]	[Automatic]
Cosmos3-Super-Image2Video-4Step	Given one or more input images and optional text instructions, generate temporally coherent video sequences	[Automatic]
Cosmos3-Super-Text2Image-4Step	Given text input, generate high-fidelity images that are consistent with the provided description.	[Automatic]
Cosmos3-Nano-Policy-DROID	Given language instructions and visual observations from the DROID robot platform, generate robot action trajectories	[Automatic]

Deployment Details:

Visit the Cosmos cookbook page for release documentation, deployment guides and more.
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.

Container Version(s):

nvcr.io/nim/nvidia/cosmos3::latest
nvcr.io/nim/nvidia/cosmos3:2.0.0

Security Common Vulnerabilities and Exposures (CVEs)

Please review the Security Scanning tab on NGC to view the latest security scan results. For certain open-source vulnerabilities listed in the scan results, NVIDIA provides a response in the form of a Vulnerability Exploitability eXchange (VEX) document. The VEX information can be reviewed and downloaded from the Security Scanning tab.

Ethical Considerations:

NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. Developers should work with their internal developer team to ensure these software components meet requirements for the relevant industry and use case and address unforeseen product misuse.

Users are responsible for model inputs and outputs. Users are responsible for ensuring safe integration of this model, including implementing guardrails as well as other safety mechanisms, prior to deployment.

Please report security vulnerabilities or NVIDIA AI Concerns here.

Get Help

Getting started with the NIM

Deploying and integrating the NIM is straightforward thanks to our industry standard APIs. Visit the Cosmos3 NIM cookbook for release documentation, deployment guides and more.