README

NVIDIA Cosmos

 World Foundation Models for Physical AI

One model family that sees, reasons, simulates, and acts.





Try it in your browser · Quickstart · Find your path · Model Family · Cookbook





  
    
      
      Physics-aware generationA Newton's cradle in motion: momentum transfer rendered with physical fidelity
    
    
      
      TransferWorld-scenario control layout → photoreal driving video
    
    
      
      Action policyPolicy run: "put the screwdriver and the glove in the purple container"
    
  
  
    
      
      SimulationGenerate synthetic data and create simulation for autonomous driving
    
    
      
      Action-conditioned World ModelForward dynamics: egocentric rollout from input camera + hand pose
    
    
      
      World reasoningReason in complex real-world scenarios: a rolling ball means a child or pet may follow
    
  


---

 What's new

- [Oct 2026]  Interactive World Simulation with Cosmos for Physical AI - example model checkpoints and training recipes: HF collection · Cookbook · Technical report · Website.
- [Jul 2026] Cosmos3-Edge released - the 4B tier for on-device, real-time deployment (Jetson AGX Orin / Thor / RTX Pro 6000).
- [May 2026] Cosmos 3 released: HF collection · Technical Report.

 What is Cosmos?

NVIDIA Cosmos is an open platform for building physical AI applications, supporting industry verticals such as robotics, autonomous vehicles, smart infrastructure, manufacturing, healthcare, agriculture. The mission of Cosmos is to provide better data, better environment, better starting point, and better tooling for physical AI developers.

Cosmos 3, the current model family, is a suite of omnimodal world models built on a unified Mixture-of-Transformers architecture (technical report).

One model, two towers:

|  | Inputs | Outputs | Use it for |
|---|---|---|---|
| Reasoner | text, vision | text | world understanding, grounding, task planning, embodied reasoning |
| Generator | text, vision, audio, action | vision, audio, action | world simulation, future prediction, synthetic data, policy learning |

This repository is the landing repo to start your physical AI journey with Cosmos. Here you can find detailed information on Cosmos models and explore Cosmos cookbook - a set of agent runnable recipes for various objectives and industries.

The recipes are supported by the Cosmos platform, including Cosmos Framework for training infra (SFT, LoRA, RL, distillation etc.), Cosmos Curator for data curation, and Cosmos Evaluator for model output evaluation.

 Find your path


  I want to…Go toTime
  See it work - zero installVideo generation, visual reasoning1 min
  Generate my first videoQuickstart ↓10 min
  Run generation/reasoning inferenceInference recipes10 min
  Serve an OpenAI-compatible APIServing guide: vLLM, vLLM-Omni, or NIM30 min
  Post-train on my own data: SFT, LoRA, distillPost-train and distill recipeshours
  Explore agent-runnable notebooksCookbookbrowse
  Evaluat