Bring your own model (Qwen running on Jetson Thor in this case) to your domain, give it the spatial harness, and boom. Any model can leverage Cactus data, spatio-semantic or any other data in your domain, and even robots or other devices.

Congratulations to Isaac Doubek, winner of the NVIDIA Jetson Thor Developer Kit giveaway at #ROSCon#. Thank you to everyone who entered and joined us at our developer meetup. It was great connecting with the community. 🤗

If the target market is real time robotics, the Jetson Thor system, with 128 GB of memory, but only 273 GB/s of bandwidth, seems over-provisioned with expensive memory. You want the model evaluating at tens of fps, so it can't use more than 10 GB of weights at most. More memory could be used if the model is a wide mixture of experts, or a large strategic planning model is operating in small time slices over a longer period of time, and more memory always makes development life easier, but for cost optimized systems, you should be able to get by with much less.

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: Learn more about it at today’s SIGGRAPH keynote—in person or via livestream at 3:45 p.m. PT:

Big day for robotics + AI! 🤖🧠 Huge congrats to @NVIDIARobotics on the official launch of Jetson Thor! ⚡ We’ve had the opportunity to get early access to the NVIDIA Jetson Thor AGX Developer Kit over the past few weeks, and we can confidently say it’s a game-changer for Apollo and for humanoid robotics

$META built a humanoid robot called Max with its CTO envisioning humanoids as “physical embodiment of Muse” capable of handling everyday household tasks. The robot runs on $NVDA Jetson Thor chip putting Nvidia at center of Meta’s push to bring AI into physical world.

Agile Robots SE has unveiled Agile ONE SN, a new humanoid reference platform designed to help researchers and developers create, train and validate robot capabilities.    Powered by NVIDIA Jetson Thor, built on Arm Neoverse V3AE CPUs, Agile ONE SN delivers onboard compute for real-time control and reasoning, while bringing simulation, training and deployment workflows together to help reduce setup time from weeks to days.   Congrats to Agile Robots and @nvidia on the announcement! 👏

NVIDIA announces new Isaac tools for agents to help developers train, test and deploy robots as Agile Robots unveils Agile ONE SN, a reference humanoid built on Isaac GR00T and powered by Jetson Thor. Read the #NVIDIAGTC# announcement: