News

NVIDIA Reveals Its Most Inexpensive Supercomputer for Generative AI

Nvidia has launched the Jetson Orin Nano Super Developer Kit, a generative AI supercomputer capable of executing up to 67 trillion operations per second. Originally introduced in 2023, it is now available for students, hobbyists, and developers worldwide.

The Jetson Orin Nano Super Developer Kit, Nvidia’s most reasonably priced generative AI supercomputer, was presented on Tuesday. This small AI accelerator, which costs $249 (about Rs 21,146), can execute up to 67 trillion operations per second (TOPS), which is more than most AI PCs that cost more than $1,000.

Students, hobbyists, and developers worldwide can currently access it. The Jetson Orin Nano Super, which retails for $499, was first introduced in 2023; therefore, this product is not new. Its price has now been lowered to $249 by Nvidia, a world leader in AI hardware and software, and the latest software upgrade has increased its performance from 40 TOPS to 67 TOPS.

Also Read: Nvidia Fugatto Text to AI Sound Model: Features, Use Cases, and Other Details

With shipping times ranging from four to five weeks, the product is already out of stock in many parts of the world.

It performs all of the functions of the Hyperscale Graphics Extension (HGX). even executes extensive language models. And I’m excited for everyone to give it a try,” Nvidia CEO Jensen Huang stated in a YouTube video.

Also Read: NVIDIA Shares Omniverse Real-Time Physics Digital Twins With Leading Software Companies

The top large language models in the world, including those from OpenAI, Meta, Google, and many more, are powered by AI accelerators made by Nvidia. The majority of small-scale developers cannot afford these accelerators, though, as the Nvidia HGX H100 costs Rs 34,00,000 or more.

The Nvidia Jetson Orin Nano Super has a graphics chip based on the Ampere architecture and a six-core Arm CPU that may provide AI inferencing. It also has 8 GB of system-on-module (SoM) memory. Additionally, it can run a variety of AI models, including transformer and sophisticated robotics models, and is compatible with any NVIDIA AI applications. It can power a range of Internet of Things (IoT) devices and is mainly made to power sophisticated robotics applications. It is also compatible with Vision AI.

Also Read: NVIDIA and SoftBank Corp. Partners to Quicken Japan’s Transition to a Global AI Powerhouse

There is no built-in storage on the Jetson Orin Nano Super. Like a Raspberry Pie, the operating system must be downloaded to a microSD card before the device can boot up.

This post was last modified on December 18, 2024 9:28 pm

Kumud Sahni Pruthi

A postgraduate in Science with an inclination towards education and technology. She always looks for ways to help people improve their lives by putting complex things into simple words through her writing.

Recent Posts

Veo 2 extends access to more Gemini Advanced Users

Google has integrated Veo 2 video generation into the Gemini app for Advanced subscribers, enabling…

April 25, 2025

Perplexity launches the iPhone voice assistant

Perplexity's iOS app now makes its conversational AI voice assistant compatible with Apple devices, enabling…

April 24, 2025

Ola’s AI arm Krutrim intends to raise $300 million

Bhavish Aggarwal is in talks to raise $300 million for his AI company, Krutrim AI…

April 22, 2025

World’s first humanoid half-marathon pits people against robots

The Beijing Humanoid Robot Innovation Center won the Yizhuang Half-Marathon with the "Tiangong Ultra," a…

April 22, 2025

Cursor AI Code Editor: How to Use, Features, Pricing and Other Details Here

Cursor AI Code Editor is more than just a coding tool; it’s a comprehensive assistant…

April 22, 2025

Ray-Ban Meta AI Smart Glasses: Features, Types and FAQs

Ray-Ban Meta AI Smart Glasses are revolutionizing wearable tech with cutting-edge features like a 12…

April 22, 2025