Nvidia introduced the Jetson Orin Nano Super single-board computer for developers of various artificial intelligence systems, including drones, robots, etc. The new product provides 70% greater performance compared to the Jetson Orin Nano and costs half the price. The Jetson Orin Nano Super delivers 67 TOPS at $249, which is a big improvement over the 40 TOPS of its $499 predecessor.
Image source: NVIDIA
The Jetson Orin Nano Super is powered by a six-core Arm Cortex-A78AE processor clocked at 1.7GHz and comes with 8GB of RAM. The 1020 MHz GPU has 1024 CUDA cores and 32 Tensor cores, delivering a maximum performance of 67 TOPS.
The system can be powered either through the USB Type-C port or through a proprietary connector, in either case, the power supply must be at least 25 W for maximum performance. The board is equipped with four USB 3.2 Type-A ports that operate at 10 Gbps, two MIPI CSI ports compatible with the Raspberry Pi camera, and M.2 2280 and M.2 2230 connectors for connecting SSDs.
The Jetson Orin Nano Super also features a 40-pin Raspberry Pi compatible GPIO header, making it possible to use Raspberry Pi Hats expansion boards. Jetson Orin Nano Super runs a specialized version of Linux – L4T, created specifically to run on Nvidia hardware. The system can be booted either from an SSD or from a microSD memory card.
According to Nvidia, the Jetson Orin Nano Super demonstrates performance gains relative to the original Jetson Orin Nano in training large language models by 37-63%, computer vision tasks by 36-104%, and image recognition by 43-69%.
Nvidia noted that its other current-generation single-board computers, including the “regular” Jetson Orin Nano, will also receive a performance boost of up to 70 percent after the software update. For example, the performance of the Orin NX 16 GB will increase from 100 to 157 TOPS, and the Orin NX 8 GB will increase from 70 to 117 TOPS.
The Nvidia Jetson Orin Nano Super single board computer will be available later this month.