Quick start guide

This section includes quick start guides for setting up your environment and running machine learning workloads on Nordic Semiconductor devices using nRF Edge AI. These pages cover common development paths, from simplified end‑to‑end solutions to lower‑level integrations with direct hardware control.

Select the guide that best matches your required level of control, tooling preferences, and target hardware. Each guide walks through the required setup steps and shows how to deploy and run an edge AI application.

If you are unsure which approach fits your use case, see the Solution overview page for a comparison of features, performance characteristics, and supported workflows.

Basic setup variants

Use these options to get started quickly or when you prefer higher‑level tooling that abstracts most of the model deployment and runtime details. These workflows rely on integrated toolchains and APIs to reduce setup effort:

  • nRF Edge AI API - Use it to train models with Nordic Edge AI Lab and deploy them with a unified API. It supports both CPU execution (Neuton) and NPU acceleration (Axon) on compatible devices. Use it for easy setup, standardized workflow, and the best Nordic Semiconductor device compatibility.

  • Edge Impulse - Use the Edge Impulse platform for an end-to-end machine learning solution. It includes visual development tools, extensive documentation, and community support. Models run on CPU or on the Axon NPU depending on the deployment target you select. Use this option if you already work with Edge Impulse or require its tooling ecosystem.

Advanced setup variants

Use these options when you need lower‑level control, custom inference pipelines, or direct access to hardware acceleration features. These workflows require more manual configuration but allow finer control over performance and resource usage.

  • Axon driver - Work directly with the Axon NPU driver API for maximum control, performance and low energy consumption. Compile TensorFlow Lite models and implement custom inference pipelines. Use this option for advanced optimization and direct NPU control.