NVIDIA Project DIGITS powered by Arm puts high-performance AI in the hands of millions of developers

Blog January 7, 2025

Project DIGITS Linux-based systems with Arm-powered CPU cores enable every AI developer to put a high-performance AI system on their desk.

One of the most exciting trends we see today is the rapid expansion and availability of AI-based applications and capabilities across a variety of edge devices. As AI continues to grow and advance, it is important that AI researchers, data scientists, developers, and students have access to high-performance computing that they can use to develop or run modern models for language, vision, multimodal, and more. . As the pace of AI innovation has never been faster, we need to make this performance accessible beyond the cloud and at the edge, delivering new capabilities directly to developers.

Making revolutionary AI performance readily available to all developers

A big step toward the vision of developing and deploying AI everywhere took place today (Monday, January 6, 2025) during NVIDIA founder and CEO Jensen Huang’s keynote at the Consumer Electronics Show (CES) 2025. NVIDIA Project DIGITS, a personal AI supercomputer announced in Project DIGITS Linux-based systems with Arm-powered CPU cores enable every AI developer to put a high-performance AI system on their desk.

NVIDIA Project DIGITS is powered by the NVIDIA GB10 Grace Blackwell Superchip, which combines NVIDIA Grace CPUs and NVIDIA Blackwell GPUs with the latest generation CUDA cores and 5th generation Tensor connected via NVLink®-C2C chip-to-chip interconnect and 128GB. Combine with core. of integrated memory. NVIDIA Grace CPUs feature the most advanced, highest-performance Arm Cortex-X and Cortex-A technology, with 10 Arm Cortex-X925 and 10 Cortex-A725 CPU cores. NVIDIA GB10 delivers up to 1 petaflops¹ (1000 TFLOPs) of AI computing performance with FP4 accuracy, enabling developers to prototype, fine-tune, infer, and deploy large AI models to the cloud. or enable them to work in conjunction with a data center.

The value of Arm computing platforms

Leverage the ubiquitous Arm compute platform to run new AI models and applications more efficiently and faster at the edge. In the consumer technology market, our CPU technology is at the heart of today’s edge devices, targeting the highest performance devices entering the market, including the latest Arm CPUs and some of the Arm Compute Subsystems used in Project DIGITS. It is designed to. (CSS) For clients. All of these technologies are optimized for maximum performance and highest efficiency across real-world applications and workloads.

The Arm computing platform also provides the flexibility to use different computational engines for different AI use cases. In NVIDIA Project DIGITS, Arm-based NVIDIA Grace CPUs and NVIDIA Blackwell GPUs play complementary roles, allowing developers to use these components for a variety of workloads. This heterogeneous computing approach is essential for maximizing AI performance while managing memory utilization and power consumption.

“Our collaboration with Arm on the GB10 superchip will power the next generation of innovation in AI, combining NVIDIA’s AI expertise with Arm’s scalable computing platform to deliver superior performance and efficiency.” NVIDIA said Ashish Karandikar, vice president of SoC products at . “With the introduction of Project DIGITS, all AI developers and researchers now have a powerful supercomputer at their fingertips.”

Unleash software innovation

For developers, it’s important to have a fully integrated hardware and software AI platform. Project DIGITS uses the open source Linux operating system, and users have access to a wide range of NVIDIA AI software, including software development tools, libraries, frameworks, and AI models available in the NVIDIA NGC Catalog and the NVIDIA Developer Portal. Access libraries to speed up generative AI. Workflow.

Arm’s NVIDIA Grace Hopper and Grace Blackwell presence in the data center provides a consistent platform architecture across both data center and edge environments, allowing developers to seamlessly use the same set of tools for AI application development . Additionally, Arm has supported and driven important work in the open source developer community to enable the software needed to bring AI everywhere. As a result, more than 20 million software developers around the world are building applications on Arm computing platforms, enabling a growing open source community to innovate at rapid scale.

The ideal platform for high-performance AI computing

Arm is the world’s leading and most popular AI computing platform today and in the future, and is ideal for the GB10 superchip used in Project DIGITS, a powerful PC desktop platform capable of running large-scale AI models of up to 200B parameters. It is a platform. This was not possible until now. This impact across the AI ​​ecosystem provides flexible, performant, and power-efficient AI capabilities to millions of developers around the world. We can’t wait to collaborate with NVIDIA and our leading software ecosystem to deploy the next generation of highly innovative AI applications.

¹ This is the FP4-based petaflops referenced here.

Written by Parag Veeraka Senior Director, Consumer Computing, Client Business Unit; arm

Permitted reuse only for informational and non-commercial or personal use.