ipXchange, Electronics components news for design engineers 1200 627

STM32 Edge AI Development Kit

Evaluation Board

ipXchange, Electronics components news for design engineers 310 310

The STM32 Edge AI Development Kit from STMicroelectronics provides an all-in-one platform for evaluating the newest STM32 microcontroller with an integrated NPU. Designed for embedded vision, machine learning, and wearable applications, this kit enables real-time AI inference with power consumption below 300 mW—making it ideal for battery-powered devices.

The board includes a 5 MP camera, display, and full suite of connectivity options, and is supported by the STM32Cube development ecosystem. ST’s onboard NPU enables high-performance inference, while software tools allow developers to benchmark model performance and estimate power usage before committing to production.

Specifications

  • MCU Core: STM32H-series with integrated NPU
  • AI Inference Support: Convolutional Neural Networks (CNN), computer vision, YOLO models
  • Operating Voltage: 3.3 V typical
  • Typical Power Consumption: <300 mW during AI inference
  • Operating Temperature Range: -40°C to +85°C
  • Supported Frameworks: TensorFlow Lite, ONNX, ST-AI suite
  • Software Tools:
    – STM32Cube.AI
    – ST Edge AI model optimiser
    – Cloud-based board farm for remote model evaluation
    – Power estimation toolkit

Onboard Components

  • Camera: 5 MP CMOS sensor
  • Display: Colour TFT (resolution and size vary by version)
  • Connectivity: USB, UART, I2C, SPI, GPIO
  • Memory: Internal Flash + optional external memory expansion
  • Additional Features:
    – Debug and programming interface via ST-LINK
    – Boot mode selection
    – ST’s power profiler integration

Evaluation Platform

ST provides an integrated cloud platform for early-stage design and benchmarking:

  • Cloud Evaluation Farm: Upload models to test performance on real STM32 NPU silicon
  • Remote Power Estimation: Profile energy consumption per model and configuration
  • Zero-Hardware Startup: Engineers can test feasibility before sourcing physical kits

The development kit is fully compatible with the STM32Cube IDE, supporting rapid prototyping, firmware development, and AI model deployment.

Applications

  • Embedded computer vision
  • Wearable AI devices
  • Low-power edge inference
  • Smart glasses
  • Industrial monitoring
  • Medical sensing systems

Availability

The STM32 Edge AI Development Kit is available globally through authorised distributors.
Refer to STMicroelectronics’ official part number: STM32H AI-NPU-KIT

Related articles

    We care about the protection of your data. Read our Privacy Policy.

    Get the latest disruptive technology news

    Sign up for our newsletter and get the latest electronics components news for design engineers direct to your inbox.