NVIDIA has unveiled a "mini-supercomputer" for enthusiasts out there, the "Jetson Orin Nano Super," which features exceptional AI performance with a sweet price tag.
NVIDIA's New "Orin" Mini-Supercomputer That Doesn't Break The Bank At All And Comes With Decent AI Performance As Well
Well, the AI hype is out there and kicking, and with commercial AI seeing massive development, hardware manufacturers would certainly present solutions that are more common to a broader audience, especially in terms of budget. The new Jetson Orin Nano Super from NVIDIA targets individuals looking to get their hands on decent AI computing power without breaking the bank. "Budget releases" by NVIDIA are often a shocker, but the newest Orin product looks excellent for commercial AI developers.
Diving a bit into specifications, the mini-supercomputer features the six-core ARM Cortex-A78E, which comes up to a 1.7 GHz boost clock and much more. Apart from this, the device offers NVIDIA's Ampere GPU with 1024 CUDA cores and 32 Tensor cores, which is instead a low-tier offering and is only ample for running the device in normal use cases. With an onboard 8 GB LPDDR5 memory and TDP of up to 25W, the Jetson Orin Nano Super is designed to focus more on AI computational performance, which we'll discuss next.
According to NVIDIA, the device comes with 67 TOPS INT8 performance, a 70% increase from the predecessor. Not only this, but the onboard 102 GB/s memory bandwidth is also a 50% increase from the previous-gen device, and when factoring in the leaps, the Jensen Orin Nano Super becomes a great option for computational needs. NVIDIA has also upscaled the Jetson lineup's software ecosystem, so the company has factored in a 1.7X generative AI performance boost for the Orin NX and Orin Nano series.
In terms of pricing, the supercomputer is available for just $249, which is surely an attractive price tag when you consider the device's performance. And since it is rare for NVIDIA to release products at such prices, the Jetson Orin Nano Super surely becomes something to look out for if you are in for budget AI performance.
About the author: Muhammad Zuhair is a hardware and technology reporter for Wccftech, specializing in the semiconductor industry and the complex interplay between technology, manufacturing, and geopolitics. His coverage focuses on the corporate strategies and technological roadmaps of industry giants like TSMC, NVIDIA, Samsung, and Intel. Zuhair's expertise lies in deconstructing complex topics such as fabrication nodes (e.g., 2nm process), the economic impact of policies like the CHIPS Act, and the strategic development of AI infrastructure from NVIDIA, AMD and Intel.
Follow Wccftech on Google to get more of our news coverage in your feeds.
