NVIDIA has outlined its push for open world models for physical AI, centred on its Cosmos 3 model family and Omniverse software tools. Physical AI differs from consumer-facing generative AI because it must account for how environments behave and what may happen next. World models help address the cost and difficulty of collecting enough real-world data, especially for unusual events and edge cases. NVIDIA is making its Cosmos world foundation models available under the Linux Foundation's OpenMDW 1.1 licence, giving developers access to model weights and allowing them to adapt the models using their own data and computing infrastructure. The Cosmos 3 family includes Cosmos 3 Super with 64 billion parameters, Cosmos 3 Nano with 16 billion, and Cosmos 3 Edge with 4 billion. NVIDIA says the Edge version is designed for deployment on devices and can run across RTX graphics processors, DGX systems and Jetson hardware, including Jetson Thor. Cosmos 3 can be used as a vision language model, a world simulator that predicts future states, or a basis for world action models. NVIDIA says the model family ranks first on Artificial Analysis for open-weights text-to-image and image-to-video generation, on PAI-Bench for world generation, and in the image-to-video category of Physics-IQ. It also ranks first on RoboLab for robot policy, while Cosmos 3 Super is the highest-ranked open model on VANTAGE-Bench for vision understanding.