Nordic Edge AI

Ultra-low-power edge AI across the industry's broadest range of applications

Your data. Your model. Your edge.

From saving bandwidth and energy to more responsive real-time performance, implementing AI in your embedded applications offers massive benefits beyond the buzzwords. Nordic Semiconductor offers two unique technologies, Neuton models and Axon NPU, exclusively to our customers, to cover the industry's broadest range of devices, applications, and customer needs.

Neuton models

Custom Neuton models are ultra-tiny edge AI models built from your data using our patented network-growing algorithm, ideal for running edge AI on any Nordic SoC or SiP using its main application core (CPU).

10×: Smaller memory footprint than TensorFlow Lite models

10×: Faster and more energy efficient than TensorFlow Lite models on the CPU

< 5 KB: Average memory footprint of custom Neuton models created with our framework

Axon NPU

The Axon NPU is our dedicated AI accelerator core, designed to increase the speed and efficiency of TensorFlow Lite models, built into our most capable SoCs.

Axon_Logo_horizontal_Gradient_RGB copy.png

15×: Faster and more energy efficient than running the same TensorFlow Lite model on the CPU

8×: More energy efficient compared to the closest competing product

7×: Faster inference than the closest competing product

Edge AI Add-on

For the nRF Connect SDK

The Edge AI Add-on for nRF Connect SDK adds all the necessary components to take advantage of the Axon NPU, as well as to integrate both custom Neuton models and models for Axon NPU in your application. The Add-on includes the common nRF Edge AI Library for inference on both CPU and NPU, drivers for Axon NPU, the Axon NPU compiler, as well as example applications showing the use of the library's APIs.

Documentation for the Edge AI Add-on is available here

Download the Edge AI Add-on

Matter + Edge AI

Add-on for the nRF Connect SDK

The Matter Edge AI Add-on for nRF Connect SDK adds a sample built on the leading smart home standard Matter, combined with voice control courtesy of our wake word and keyword spotting technologies. The sample runs entirely on the nRF54LM20B SoC, using the Axon NPU for AI inference of wake word and keywords, while the Matter light switch application runs on the main Arm Cortex CPU.

To use the voice controlled light switch you use the wake word "okay Nordic" to enable keyword spotting, then you select one of the five commands: "toggle lights" and "scene 1" through "scene 4". Scenes are configured in your Matter ecosystem.

Documentation for the Matter Edge AI Add-on and details on how to try out the voice controlled light switch is available here.

Download the Matter Edge AI Add-on

General software development

nRF Connect SDK

nRF Connect SDK is a common software development kit for Bluetooth Low Energy, Wi-Fi, cellular IoT, Bluetooth mesh, Thread, Zigbee and Matter. It supports all our nRF52, nRF53, nRF54L, nRF70 and nRF91 Series wireless devices.

nRF Connect for VS Code

nRF Connect for VS Code lets you develop, build, and debug applications based on the nRF Connect SDK using the VS Code Integrated Development Environment (IDE).