Compile your own model

Edge AI Lab

tags
edge-ai-lab

This page describes how to compile an existing LiteRT model for the Axon NPU in Nordic Edge AI Lab. Use this option if you already have a trained .tflite model and want to estimate how it will perform on the Axon NPU, rather than training a new model in the lab.

This is the fastest way to get a footprint estimate — no local installation required.

Compile for Axon NPU

Note

Only fully integer-quantized (int8) LiteRT (.tflite) models are accepted. Other quantization schemes are not supported.