NVIDIA brings Thor modules to robotics and edge AI

NVIDIA introduced the T3000 and T2000, new modules based on its Thor architecture for mainstream robotics and edge AI deployments. Jetson AGX Thor is already being used by companies including 1X, Agile Robots, Amazon Robotics, Boston Dynamics, FANUC, Hitachi and Techman Robot for humanoid and robotic systems.

The Jetson and IGX T3000 modules deliver 865 FP4 teraflops of AI compute in a compact form factor roughly half the size and power of the T5000. Jetson T3000 combines an NVIDIA Blackwell GPU, an eight-core Neoverse Arm CPU, 32GB of LPDDR5X memory, 273GB/s of memory bandwidth and 25 GbE connectivity, while IGX T3000 adds integrated functional safety and runs NVIDIA Halos for Robotics.

Jetson T2000 targets a wider set of edge systems with 400 FP4 teraflops of compute and 16GB of memory. NVIDIA said the expanded Jetson lineup now spans performance from 70 TOPS to 2,000 teraflops, covering workloads such as visual AI agents, autonomous mobile robots and industrial manipulators.

NVIDIA also released Jetson agent skills to automate memory optimization across Jetson Thor and Jetson Orin, and expanded Cosmos 3 with Cosmos 3 Edge, a 4-billion-parameter model for on-device inference. T3000 emulation mode is due later this month with JetPack 7.2.1, T2000 emulation will follow later, and both modules are scheduled for Q1 2027.