Ultra-Low-Power Edge AI

Across the industry's broadest range of applications

Implementing AI at the edge unlocks measurable gains, from energy and bandwidth efficiency to highly responsive real-time performance. Nordic Semiconductor uniquely combines Neuton models and the Axon NPU, available exclusively to our customers, to address the broadest spectrum of devices, applications, and AI deployment requirements across the industry.

Introducing Ultra-Efficient Edge AI Models

Ultra-Efficient AI Acceleration in nRF54L Series

Neuton Models

The Neuton Models Solution

Custom Neuton models takes a radically different approach. Instead of starting with a predetermined structure, it grows neural networks neuron-by-neuron, automatically determining the optimal architecture as it learns. This granular construction process, combined with a patented global optimization algorithm that avoids the pitfalls of traditional gradient descent methods, produces remarkably compact models without sacrificing accuracy.

Key Features and Performance

10x Smaller memory footprint than TensorFlow Lite models
10x Faster and more energy efficicent than running TensorFlow Lite models on the CPU
< 5 KB Average memory footprint of custom Neuton models created with our framework

Featured Products

nRF54LM20A SoC Ultra-low-power wireless SoC supporting Bluetooth LE, Channel Sounding, Bluetooth Mesh, Zigbee, Thread, Matter, Aliro, and 2.4 GHz proprietary protocols

nRF54L15 SoC Ultra-low-power wireless SoC supporting Bluetooth LE, Bluetooth Channel Sounding, Bluetooth Mesh, Zigbee, Thread, Matter, Amazon Sidewalk and 2.4 GHz proprietary protocols

nRF54L10 SoC Ultra-low-power wireless SoC supporting Bluetooth LE, Bluetooth Channel Sounding, Bluetooth Mesh, Zigbee, Thread, Matter, Amazon Sidewalk and 2.4 GHz proprietary protocols

Axon NPU

Simpler designs and broader possibilities

By integrating the NPU on-chip, Axon removes the need for discrete accelerators, reducing power, BoM cost, and development complexity. Axon enables industry-leading energy efficiency across use cases ranging from anomaly detection and biometrics to sound, keyword, and image recognition – leveraging fully accelerated edge AI.

Key Features and Performance

15x Faster and more energy efficient than running the same TensorFlow Lite model on the CPU
8x More energy efficient compared to the closest competing product
7x Faster inference compared to the closest competing product