Nvidia introduced the Jetson Orin Nano 2, a small robotics computer aimed at delivery drones, inspection robots, and vision AI systems. It delivers 78 trillion operations per second of AI compute, 8 GB of memory, and an 8-core Arm CPU, offering twice the inference performance of the Jetson Orin Nano Super while using 40% less power at the same performance in 15-watt mode. It supports open models like Cosmos, Nemotron, Gemma 4, and Qwen 3 for local, real-time inference. An ecosystem of over 20 hardware partners is already building carrier boards and reference designs, and companies like Cognex, Doosan Bobcat, and Matic are early adopters. The module and developer kit ship in the first half of 2027.
Questions this post answers
What are the specs of the Nvidia Jetson Orin Nano 2 compared to the Jetson Orin Nano Super?
The Jetson Orin Nano 2 delivers 78 trillion operations per second of AI compute, 8 GB of memory, and an 8-core Arm CPU, achieving twice the inference performance of the Jetson Orin Nano Super in the same form factor thanks to improved Tensor Cores and higher memory bandwidth. It also uses 40% less power at the same performance level in 15-watt mode. daily.dev helps edge AI developers track hardware releases like Jetson upgrades before they ship.
When will the Nvidia Jetson Orin Nano 2 be available and what models can it run?
The Jetson Orin Nano 2 module and developer kit ship in the first half of 2027. It supports open large language and vision language models optimized for memory-efficient edge inference, including Cosmos, Nemotron, Gemma 4, and Qwen 3, running locally in real time on the device. Robotics developers planning around new hardware timelines can follow updates like this on daily.dev.