Practical Guide to Implementing Edge AI with ST's First Microcontroller Featuring NPU
We will explain the STM32N6, the first microcontroller with an NPU from ST, from a practical perspective. This includes the architecture of the Neural-ART Accelerator (1GHz, up to 600 GOPS, approximately 3 TOPS/W), criteria for differentiating its use from Jetson/Raspberry Pi, how to choose evaluation boards, deployment procedures for ONNX models, memory constraints with 4.2MB SRAM and flashless configuration, and key points for mass production adoption. This will be explained by TechnoSphere, which has engineers with over 20 years of embedded development experience. For more details, please refer to the technical column in the related links.
Inquire About This Product
basic information
【Target】 - STM32N6 (equipped with Neural-ART NPU) 【Technical Elements】 - Neural-ART Accelerator (up to 600 GOPS, approximately 3 TOPS/W) - Deployment procedure for ONNX models - Memory constraints of 4.2MB SRAM / flashless configuration - Differentiation between Jetson and Raspberry Pi 【Category】Embedded Systems / Edge AI *We will explain from a practical perspective up to the decision points for mass production adoption.
Price range
Delivery Time
Applications/Examples of results
【Intended Use】 - Development of edge AI devices that operate with a microcontroller alone - On-device inference for images and signals - Mass production of low-power AI edge products 【Examples of Achievements】 - Accumulated evaluation and deployment know-how for microcontrollers equipped with NPUs through edge AI and embedded contract development.
Company information
Technosphere Co., Ltd. is a system development company based in Osaka that tackles customer challenges in advanced technology areas such as AI, IoT, and web system development. Since its founding in 2021, the company has leveraged a flat team structure to achieve a flexible and speedy development style. We are engaged in solutions that directly address social issues, such as image inspection AI and smart factory support systems.






![x86 Edge AI Platform [DLAP-4100 Series]](https://image.mono.ipros.com/public/product/image/431/2001538294/IPROS6298779451751543553.jpg?w=280&h=280)



