NVIDIA details four open-weight Cosmos 3 checkpoints for driving and robot simulation

NVIDIA released four open-weight Cosmos 3 Nano checkpoints on Hugging Face on November 5th, 2026, each a post-trained model with 16B trainable parameters under OpenMDW 1.1 terms permitting commercial and non-commercial use. The checkpoints target multi-view driving data, synchronized camera-LiDAR streams, simulator-to-video rendering and two-arm robot prediction, extending the Cosmos 3 family into streaming driving simulation and action-conditioned robot video. NVIDIA says the open, task-specific world models lower the cost of generating rare driving conditions and robot training scenes without physically collecting every case.

NVIDIA details four open-weight Cosmos 3 checkpoints for driving and robot simulation NVIDIA's 16B post-trained models cover multi-view driving data, synchronized camera-LiDAR streams, simulator-to-video rendering and two-arm robot prediction. By Ryan Merket https://runtimewire.com/author/ryan-merket · Published · Updated Primary source: Hugging Face Newsroom https://huggingface.co/blog/nvidia/cosmos-interactive-world-simulation Why it matters Open, task-specific world-model checkpoints lower the cost of generating rare driving conditions and robot training scenes without collecting every case physically. The commercial-use license and adaptation recipes make the release usable inside company simulation stacks. NVIDIA added four open-weight Cosmos 3 Nano checkpoints to Hugging Face https://huggingface.co/blog/nvidia/cosmos-interactive-world-simulation?ref=runtimewire on November 5th, 2026, extending the Cosmos 3 family into streaming driving simulation and action-conditioned robot video. The four releases are post-trained versions of Cosmos 3 Nano, each with 16B trainable parameters, released under OpenMDW 1.1 terms that permit commercial and non-commercial use.… When you purchase through links in our articles, we may earn a small commission https://runtimewire.com/affiliate-monetization-standards . This doesn’t affect our editorial independence.