NVIDIA has released the Jetson Orin Nano Super Developer Kit, a compact generative AI supercomputer. The device is small enough to fit in your hand and improves the performance of generative AI features.
Jetson Orin Nano Super delivers up to 1.7x the previous generation’s generative AI inference performance, with 70% higher INT8 performance to 67 TOPS and 50% higher memory bandwidth to 102GB/s. It features an NVIDIA Ampere architecture GPU with tensor cores, a 6-core Arm CPU, and supports up to 4 cameras with higher resolutions and frame rates.
The platform is compatible with NVIDIA’s AI software ecosystem, including tools such as NVIDIA Isaac for robotics, NVIDIA Metropolis for vision AI, and NVIDIA TAO Toolkit for model fine-tuning. It also integrates with NVIDIA Omniverse Replicator to generate synthetic data and benefits from additional support from an active developer community and partner ecosystem.
Jetson Orin Nano consists of an 8GB system-on-module (SoM) and a reference carrier board, suitable for prototyping edge AI applications. In addition, the software update will also improve production AI performance by up to 1.7x for existing Jetson Orin Nano developer kit owners as well as Jetson Orin NX and Orin Nano series systems on the module. This update is available through the JetPack SDK.
This announcement received a lot of attention from the technology community. Amorphic founder Graham Cooke shared on his X account:
This means that AI can run without being connected to the cloud. And it’s about to spark the biggest technology war of our time.
Marios Karatsias, on the other hand, highlighted the impact on robotics, saying:
Since we are in the age of robots, NVIDIA has “cooked” processors suitable for #robotics.
The Jetson Orin Nano Super Developer Kit makes generative AI at the edge more accessible, unlocking new possibilities for robotics, vision AI, and multimodal applications. Available now through authorized NVIDIA resellers worldwide.
