TI expands MCUs for edge AI
Texas Instruments expanded MCU families aimed at bringing edge AI into every device — the March 28 post positions MCUs as the on‑device compute layer for faster time‑to‑market. (x.com) That fits broader forecasts that cellular IoT connections will double by 2030, with SoC modules enabling more on‑device compute and faster market entry. (x.com)
TI named the two new MCU families as the MSPM0G5187 and AM13Ex and said both integrate its TinyEngine neural processing unit to accelerate on‑device inference. (ti.com) TI claims the TinyEngine NPU delivers up to 90× lower latency and more than 120× lower energy per inference compared with similar MCUs that lack a hardware accelerator. (marketscreener.com) The MSPM0G5187 is built on an Arm Cortex‑M0+ core and TI lists it as available in production quantities on TI.com, while the AM13E23019 is in preproduction and TI plans additional package and memory variants by the end of 2026. (eetasia.com) TI is packaging development support around the launch, adding generative‑AI features to its Code Composer Studio IDE and publishing more than 60 models and application examples in CCStudio Edge AI Studio to speed prototype development. (ti.com) The company debuted the MCUs at Embedded World in Nuremberg (March 10–12, 2026) and quoted Amichai Ron, senior vice president of Embedded Processing and DLP Products, framing the TinyEngine rollout as a company‑wide integration across its MCU portfolio. (vmblog.com)
