Nordic Semiconductor announced a comprehensive ultra-low-power Edge AI solution that brings on-device intelligence to even the smallest battery-powered IoT devices, combining energy efficiency with simplified development. Central to the launch is the new nRF54LM20B SoC, the first large-memory device in the nRF54L Series, integrating the Axon Neural Processing Unit (NPU) acquired through Nordic’s 2023 Atlazo acquisition, delivering up to 7× faster performance and up to 8× higher energy efficiency for demanding edge AI workloads. Complementing the hardware are ultra-tiny Neuton edge AI models, typically under 5 KB, and the Nordic Edge AI Lab, which enables developers to quickly build and deploy custom models for real-time, privacy-preserving intelligence without cloud dependency.
Also Read: Innodisk and Qualcomm Partner on AI Dragonwing Computing Series
“AI factories train intelligence, but Nordic deploys it – on device, at the edge, where the world happens,” said Vegard Wollan, CEO at Nordic Semiconductor. “Edge AI is no longer optional – it’s the only way to deliver safety, privacy, and sustainability at scale.” Reinforcing the developer-first approach, Oyvind Strom, EVP Short-Range BU at Nordic Semiconductor, added, “With Nordic Edge AI Lab, Neuton models, and the Axon NPU, Nordic makes advanced on-device AI practical for every embedded developer.”