NextComputing and Ampere Bring AI to the Edge for Cyber Threat Hunting
14 February 2025
NextComputing sought to equip defense and cyber response teams with powerful, portable AI for in-field threat hunting. Traditional solutions were bulky and power-hungry, hindering effective mobile operations. By integrating Ampere® Altra® processors, NextComputing created the Nexus Fly-Away Kit: a compact, carry-on system delivering scalable AI inferencing with up to 512 cores. This innovation empowers teams with rapid, AI-driven response capabilities for critical missions, transforming edge cybersecurity.
NextComputing designs and manufactures high-performance portable computing solutions for AI, networking, storage, and real‑time processing. With deep expertise in cybersecurity, the company builds ruggedized systems like the Nexus Fly-Away Kit, enabling dense, energy-efficient Ampere-based compute at the edge. NextComputing emphasizes scalability, mobility, and low-latency performance, empowering defense and enterprise teams to deploy secure, mission-ready AI analytics that accelerate decisions while minimizing size, weight, and power for field operations in austere or disconnected environments worldwide with rapid deployment.
Challenges
Deploying AI for cyber threat hunting at the edge presented significant hurdles. Legacy systems were power-hungry, generated excessive heat, and failed to meet size, weight, and power (SWaP) demands for portable use. NextComputing needed a solution maximizing AI inferences per watt, parallelizing workloads across many cores, and supporting large memory for LLMs like H2O Danube.
Solution
NextComputing leveraged Ampere Altra processors to build the Nexus Fly-Away Kit. This compact, portable solution delivers up to 512 cores per carry-on for efficient AI inference and large memory support. It eliminates bulky multi-box setups, allowing AI models like H2O Danube to run effectively at the edge. Rancher Government Solutions manages the cluster for quick deployment.
Benefits
The Nexus Fly-Away Kit provides a portable AI compute cluster for complex, heterogeneous workloads. Ampere processors deliver high-performance AI inference per watt, ensuring energy efficiency for edge deployments. With up to 512 cores and large memory, it processes parallel AI workloads seamlessly, providing high throughput for LLMs like H2O Danube in a compact carry-on, boosting edge reliability for threat neutralization.
“Ampere Altra Max processors have completely changed how we bring AI to the edge. Instead of relying on bulky, power-hungry multi-box setups, deployed teams can have a solution that leverages the Nexus with Ampere for real-time AI inference in a compact, energy-efficient form factor.”
About Ampere
Ampere is a semiconductor design company for a new era, leading the future of computing with an innovative approach to CPU design focused on high-performance, energy efficient AI compute. As a pioneer in the new frontier of energy efficient high-performance computing, Ampere is part of the Softbank Group of companies driving sustainable computing for AI, Cloud, and edge applications.
See our solutions for a variety of demanding workloads: amperecomputing.com/solutions
Visit our Developer Center: amperecomputing.com/developers
Disclaimer
All data and information contained in Disclaimer: All data and information contained in or disclosed by this document are for informational purposes only and are subject to change. This document may contain technical inaccuracies, omissions and typographical errors, and Ampere is under no obligation to update or correct this information. Ampere makes no representations or warranties of any kind, including express or implied guarantees of noninfringement, merchantability, or fitness for a particular purpose, and assumes no liability of any kind. All information is provided “AS IS.” This document is not an offer or a binding commitment by Ampere.
This document is not to be used, copied, or reproduced in its entirety, or presented to others without the express written permission of Ampere®.