License YOLO
Technology partner

Bringing embedded vision AI to the edge with STMicroelectronics

Ultralytics and STMicroelectronics bring real-time YOLO inference to STM32N6 microcontrollers, with the Neural-ART Accelerator™ NPU.

Ultralytics and STMicroelectronics partner to power edge AI. Deploy YOLO vision models on ST hardware for industrial, automotive, and IoT applications.

About STMicroelectronics

STMicroelectronics is a global leader in semiconductor technology, with over 50,000 employees and more than 200,000 customers worldwide. The company designs and builds chips that power everything from electric vehicles and industrial equipment to smart home devices and consumer electronics. With the launch of the STM32N6, a high-performance microcontroller featuring the in-house Neural-ART Accelerator™ NPU, STMicroelectronics is bringing AI capabilities directly to low-power embedded devices, enabling a new generation of intelligent applications at the edge.

Why choose the STM32N6 for Ultralytics YOLO?

Optimized for Ultralytics YOLO

YOLO support on the STM32N6, with multiple model variants ready for embedded deployment.

Edge-native performance

Real-time inference with the Neural-ART Accelerator™ NPU, for embedded AI workloads.

Real-time inference

On-device inference with real-world speed and reliability.

Battery-powered efficiency

Run YOLO models in real time on battery-powered devices with the efficiency of the STM32N6.

Easy integration

Seamless workflow through STM32Cube AI Studio, with full toolchain YOLO model support.

Scalable edge AI

Increased adaptability for vision AI solutions across industries.

The complete solution

Build and refine your custom YOLO models on Ultralytics Platform. From Ultralytics YOLOv8 to YOLO26, access state-of-the-art architectures, curated datasets, and powerful optimization tools, all designed to get you to production faster.
Convert and quantize your trained Ultralytics YOLO model for STM32N6 deployment using STM32Cube AI Studio, optimizing it for the Neural-ART Accelerator™ NPU.
Run your optimized model directly on the STM32N6 microcontroller, delivering real-time vision AI with minimal power draw. It is ideal for smart cities, healthcare, industrial automation, and consumer electronics.
Train with Ultralytics YOLO

Frequently asked questions

  • We work with established hardware, cloud and robotics companies, enterprise software platforms with an active user base, and system integrators deploying vision AI at production scale.

  • Early-stage startups can join our Startup program, students and community builders our Ambassador program, and anyone can license YOLO to build with it today.

  • Strategic partners work with us on joint engineering and go-to-market. Technology partners have a supported YOLO integration documented in our docs.

  • YOLO exports to formats such as ONNX, TensorRT, OpenVINO, CoreML and LiteRT, so it runs on CPUs, GPUs, NPUs and edge devices. See all integrations in our docs.

  • Ultralytics YOLO is available under AGPL-3.0, which requires you to open-source your project, or under an Enterprise license for private and commercial use.