NVIDIA releases Cosmos 3 Edge, a 4B-parameter open world model for robots on Jetson and RTX hardware
AI video model releases
NVIDIA releases Cosmos 3 Edge, a 4B-parameter open world model for robots on Jetson and RTX hardware
NVIDIA released Cosmos 3 Edge, a 4-billion-parameter open world model on Hugging Face for edge robotics and vision AI agents
The model runs on NVIDIA edge hardware including RTX PRO GPUs, DGX, GeForce RTX GPUs, and Jetson modules, including the newly announced Jetson T2000 and T3000
As a post-trained world action model, it operates at 640x360 resolution and generates 32 actions per inference on Jetson Thor, achieving real-time control at 15 Hz
Among 4B-parameter models, Cosmos 3 Edge ranks number 1 on VANTAGE-Bench for vision analytics and claims state-of-the-art results for robot policy learning
The architecture combines two transformer towers, an autoregressive tower for vision and text reasoning and a diffusion tower for prediction and action generation, sharing multimodal attention layers
cho.sh