News
Launches Jetson Orin Nano Super, Boosting Generative AI Performance
- By John K. Waters
- 12/18/2024
NVIDIA unveiled its most affordable compact generative AI supercomputer this week, delivering enhanced performance at a lower price point for developers, hobbyists, and students.
The new Jetson Orin Nano Super Developer Kit offers up to a 1.7x gain in generative AI performance over its predecessor and is priced at $249, a significant drop from the previous $499 model. Available immediately, the palm-sized kit supports popular generative AI models, robotics, and computer vision applications, positioning itself as a versatile platform for AI development.
NVIDIA’s latest kit delivers 67 INT8 TOPS (trillions of operations per second) for inference tasks — a 70% increase — along with 50% higher memory bandwidth, reaching 102GB/s. It is suited for tasks like building large language model (LLM) chatbots with retrieval-augmented generation, developing visual AI agents, or deploying AI-driven robotics systems.
The Jetson Orin Nano Super includes an NVIDIA Ampere GPU with tensor cores and a 6-core Arm CPU, enabling simultaneous AI application pipelines and high-speed inference. Supporting up to four cameras at higher resolutions and frame rates, the kit caters to edge AI prototyping.
NVIDIA also rolled out software updates that unlock the same 1.7x performance boost for existing Jetson Orin Nano and Orin NX devices through an updated JetPack SDK, extending the performance gains across its product range.
The Jetson Orin Nano Super integrates with NVIDIA's AI ecosystem, including tools such as NVIDIA Isaac for robotics, NVIDIA Metropolis for vision AI, and NVIDIA Holoscan for sensor processing. Developers can accelerate projects using Omniverse Replicator for synthetic data generation and the NVIDIA TAO Toolkit for fine-tuning pretrained AI models.
NVIDIA also highlighted its collaboration with ecosystem partners, offering additional tools, sensors, and development support for custom applications.
The kit’s launch aligns with the industry’s growing demand for accessible AI development platforms as foundation models — capable of supporting diverse AI tasks — gain traction.
NVIDIA’s Jetson platform, supported by a robust developer community and open-source resources, positions itself as an entry point for generative AI innovation, robotics, and computer vision applications.
About the Author
John K. Waters is the editor in chief of a number of Converge360.com sites, with a focus on high-end development, AI and future tech. He's been writing about cutting-edge technologies and culture of Silicon Valley for more than two decades, and he's written more than a dozen books. He also co-scripted the documentary film Silicon Valley: A 100 Year Renaissance, which aired on PBS. He can be reached at jwaters@converge360.com.