Cisco Unveils Device to Run AI Locally

Cisco Systems has introduced its latest computing platform, the Cisco Unified Edge, designed to enable artificial-intelligence workloads to be processed directly at the edge—such as in retail outlets, factory floors or healthcare facilities—rather than relying solely on distant cloud data centres.

Built to handle the surge in “agentic” and reasoning-model AI traffic, the Unified Edge features an Intel chip and is already in pilot use by Verizon Communications. It combines computing, storage and networking elements—including modular CPU/GPU options, high-performance SD-WAN networking, and pre-validated application stacks—into a single, edge-optimised chassis.

According to Cisco’s chief product officer Jeetu Patel, as AI agents become more embedded into everyday settings, the infrastructure “will naturally emerge closer to where customers interact and decisions are made.” The device is expected to be widely available by the end of the year. 

With enterprises increasingly focused on latency, data-sovereignty and cost constraints of centralised AI infrastructure, the Unified Edge marks a strategic push by Cisco toward distributed intelligence at the network edge.