Nvidia launches Jetson Orin Nano 2, with inference performance doubling compared to the previous generation

Odaily Planet Daily News Chip manufacturer Nvidia released the Jetson Orin Nano 2 for edge AI on August 26, with plans to bring it to market in the first half of next year. The product delivers 78 TOPS of computing power, equipped with 8GB of memory and an eight-core Arm CPU, targeting energy-efficient video processing scenarios.

The Jetson Orin Nano 2 doubles the inference performance of the previous Jetson Orin Nano Super, using the same form factor with upgraded Tensor Cores and memory bandwidth. Power consumption is reduced by 40% in its 15-watt mode.

Cognex, Doosan Bobcat, Matic, and Wing are potential customers for the product, as these companies are applying AI capabilities to smart drones, home robotics, and vision AI applications. Nvidia is also offering carrier boards, hardware systems, reference solutions, and software support for large language models and vision language models, supporting open models such as Nvidia Cosmos, Nemotron, Gemma 4, and Qwen 3. (TheElec)