NVIDIA Cosmos 3 unifies physical AI into one 32B omni-model
nvidia released cosmos 3, a 32b parameter mixture-of-transformers model that unifies world generation, reasoning, and policy tasks into a single architecture. this enables developers to build physical ai systems for robotics and autonomous driving that understand physics and causality without managing separate models.
nvidia introduced cosmos 3, the first open omni-model foundation for physical ai, shifting from separate models for prediction, transfer, and policy to a single architecture built on a mixture-of-transformers backbone. by processing text, image, video, audio, and action inputs within shared parameter sets that handle both autoregressive reasoning and diffusion generation, the model can simulate physical worlds, predict outcomes, and generate robot policies simultaneously. available in 8b and 32b parameter sizes on hugging face, the model is optimized for generating synthetic data for robotics and autonomous vehicles. this release significantly reduces the complexity of training physical ai systems, enabling developers to deploy physically accurate simulations on hardware ranging from rtx pro 6000 gpus to nvidia hopper and blackwell clusters.