Reactions from ranked influencers
6 posts
Excited to share: NVIDIA Cosmos 3 Edge is openly available, bringing frontier world models to NVIDIA Jetson Thor and other local devices for physical AI. Read the blog: https://nvda.ws/3QX3LKk Learn more about it at today’s SIGGRAPH keynote—in person or via livestream at 3:45 p.m. PT: https://nvda.ws/4yxUKIz
We’re introducing Cosmos 3 Edge, an open frontier world model built to run on-device. With 4B parameters and a 2B Nemotron-based reasoner, it brings video understanding, prediction, simulation, reasoning, and action to robots, autonomous vehicles, and vision agents at the edge.
Introducing Cosmos 3 Edge: our open frontier world model built to run on-device. Cosmos 3 Edge helps robots learn and act, autonomous vehicles understand road scenes and predict intent, and vision AI agents reason across live video for smart infrastructure. With 4B parameters and a 2B Nemotron-based reasoner, you can run it on DGX Spark, NVIDIA Jetson, and more.
Excited to share: NVIDIA Cosmos 3 Edge is openly available, bringing frontier world models to NVIDIA Jetson Thor and other local devices for physical AI. Read the blog: https://nvda.ws/3QX3LKk Learn more about it at today’s SIGGRAPH keynote—in person or via livestream at 3:45 p.m. PT: https://nvda.ws/4yxUKIz
Excited to share: NVIDIA Cosmos 3 Edge is openly available, bringing frontier world models to NVIDIA Jetson Thor and other local devices for physical AI. Read the blog: https://nvda.ws/3QX3LKk Learn more about it at today’s SIGGRAPH keynote—in person or via livestream at 3:45 p.m. PT: https://nvda.ws/4yxUKIz
Cosmos 3 Edge combines autoregressive and diffusion transformer towers through shared multimodal attention, connecting understanding, prediction, simulation and action in one model. You can find a full technical breakdown of Cosmos 3 Edge below. https://nvda.ws/3RoJNIj
Introducing Cosmos 3 Edge: our open frontier world model built to run on-device. Cosmos 3 Edge helps robots learn and act, autonomous vehicles understand road scenes and predict intent, and vision AI agents reason across live video for smart infrastructure. With 4B parameters and a 2B Nemotron-based reasoner, you can run it on DGX Spark, NVIDIA Jetson, and more.