Nvidia has introduced the Jetson Orin Nano 2, a compact computer designed for robotics and edge AI. The new model offers double the inference performance while maintaining the same form factor, enabling the execution of modern language and multimodal models directly on the device.
Twice as Fast
The Jetson Orin Nano 2 is equipped with an 8-core Arm processor, 8 GB of memory, and delivers AI computing performance of up to 78 TOPS. According to Nvidia, the improved Tensor Cores and higher memory bandwidth provide twice the inference efficiency compared to the Jetson Orin Nano Super.
The company has retained the compact form factor of the previous version. In 15W power mode, the Jetson Orin Nano 2 maintains the same performance level while consuming 40% less energy.
This is particularly important for devices operating at the edge, such as robots, drones, and computer vision systems, which need to process data in real-time without constantly sending information to the cloud.
AI Inside the Robot
Nvidia positions the Jetson Orin Nano 2 as a platform for physical AI systems capable of perceiving the environment, reasoning, and acting autonomously.
The computer supports modern edge-optimized inference models, including NVIDIA Cosmos, NVIDIA Nemotron, Gemma 4, and Qwen 3. Developers can use these for image and speech recognition, navigation, human interaction, and decision-making directly on the device.
Nvidia notes that advanced compact models can now achieve accuracy comparable to larger systems of the previous generation, allowing more generative AI functions to be transferred from data centers directly to devices.
Focus on Mass Robotics
Nvidia reports that over 3 million developers are already using its robotics stack.
Among the first companies to implement or test the Jetson Orin Nano 2 are machine vision system manufacturer Cognex, equipment manufacturer Doosan Bobcat, and robotics company Matic. The latter uses the platform for home robots that need to map rooms, recognize objects, interact with people, and perform tasks autonomously.
Another application is autonomous drones. Wing, a subsidiary of Alphabet, uses the previous generation Jetson Orin Nano in its delivery systems and plans to evaluate the new version to enhance data processing speed and energy efficiency of drones.
Nvidia aims to make generative and agent AI accessible not only to large robotics companies but also to developers of relatively small autonomous devices. The Jetson Orin Nano 2 occupies the lower segment of the lineup but offers computing capabilities that previously required much more to run modern models on the device itself.
Earlier, ACE Robotics Chairman Wang Xiaogan predicted a “ChatGPT moment” for robots based on embodied AI by the end of 2027.
