NVIDIA has announced the Jetson Orin Nano 2, a new robotics computer designed to put frontier-class generative AI performance into the hands of millions of edge developers. The module delivers 78 trillion operations per second (TOPS) of AI compute, 8GB of memory, and an 8-core Arm CPU — in the same compact form factor as its predecessor.
The performance gains are substantial: Jetson Orin Nano 2 achieves 2x the inference performance of the Jetson Orin Nano Super through improved Tensor Cores and higher memory bandwidth. In 15-watt mode, it consumes 40% less power to deliver the same performance as before. NVIDIA says the combination makes it possible to run the latest large language models and vision language models directly on edge devices — including open models like Nemotron, Gemma 4, and Qwen 3.
"Today's small and medium frontier models have reached the accuracy of last year's largest frontier models, unlocking real-time intelligence for edge devices," said Deepu Talla, NVIDIA's vice president of robotics and edge AI. "The Jetson Orin Nano 2 puts that breakthrough within reach of millions of developers."
More than 3 million developers are already building on NVIDIA's robotics stack. Among the first adopters of Jetson Orin Nano 2 are Wing, Alphabet's drone delivery subsidiary, which plans to use it to advance real-time AI perception and reasoning for faster, safer residential deliveries. Matic Robots, a consumer home cleaning robot company, is adopting it to enable conversational AI, gesture detection, precision mapping, and autonomous cleaning.
The Jetson ecosystem includes over 20 partner companies — AAEON, ADLINK, Advantech, Aetina, Seeed Studio, and others — building carrier boards, hardware systems, and reference solutions to help customers bring products to market faster.
The Jetson Orin Nano 2 module and developer kit are expected to be available in the first half of 2027, with early adopters already building and testing applications on the platform.
