Robotics computer doubles edge AI performance
NVIDIA’s Jetson Orin Nano 2 system-on-module delivers nearly twice the inference performance of its predecessor, the Jetson Orin Nano Super. The performance boost comes from improved Tensor Cores and higher memory bandwidth. Nano 2 also maintains the same compact form factor as the Nano Super while consuming 40% less power in 15-W mode.
The robotics computer enables developers to build robots, delivery and inspection drones, and vision AI systems with advanced generative AI capabilities. NVIDIA says the Nano 2 combines up to 78 TOPS of AI performance, 8 GB of memory, and an 8-core Arm CPU in a cost-effective, power-efficient design.
Built on NVIDIA’s open software stack and supported by Jetson agent skills and a rich AI ecosystem, Jetson Orin Nano 2 allows developers to run the latest large language models (LLMs) and vision language models optimized for memory-efficient edge inference. These include open models such as NVIDIA Cosmos, NVIDIA Nemotron, Gemma 4, and Qwen 3.
The NVIDIA Jetson Orin Nano 2 module and developer kit are expected to be available in the first half of 2027.
The post Robotics computer doubles edge AI performance appeared first on EDN.
