New MCUs with TinyEngine™ NPU join TI’s comprehensive portfolio of AI-enabled hardware, software and tools, enabling engineers to bring intelligence anywhere
News highlights:
- TI’s integrated TinyEngine NPUs can run AI models with up to 90x lower latency and more than 120x lower energy usage per inference than similar MCUs without accelerators.
- TI’s new general-purpose real-time MCUs include TinyEngine NPUs that enable more efficient edge AI in any application, from simple to complex systems.
- With generative AI integrated into TI’s CCStudio™ IDE and over 60 models and application examples in CCStudio Edge AI Studio, developers can quickly and easily add edge AI to any device.
dallas, March 10, 2026 /PRNewswire/ — Texas Instruments (TI) (Nasdaq: TXN) today announced two new microcontroller (MCU) families with edge artificial intelligence (AI) capabilities to support the company’s efforts to enable edge AI across its embedded processing portfolio. The MSPM0G5187 and AM13Ex MCUs integrate TI’s TinyEngine neural processing unit (NPU). It is an MCU-specific hardware accelerator that optimizes deep learning inference operations to reduce latency and improve energy efficiency when processing at the edge.
TI integrates TinyEngine NPUs across its entire microcontroller portfolio, including general-purpose MCUs and high-performance real-time MCUs.
For more information, see ti.com/edgeAI, ti.com/MSPM0G5187, and ti.com/AM13E23019.
TI’s embedded processing portfolio is supported by a comprehensive development ecosystem, including the CCStudio integrated development environment (IDE). Its generative AI capabilities enable engineers to use a simple language to accelerate code development, system configuration, and debugging through industry-standard agents and models combined with TI data. Overall, TI is accelerating the adoption of edge AI into all electronic devices, from real-time monitoring in wearable health monitors and home circuit breakers to physical AI in humanoid robots. These end-to-end innovations will be showcased at the TI booth at embedded world 2026, March 10-12 in Nuremberg, Germany.
“TI invented the digital signal processor nearly 50 years ago, laying the foundation for today’s edge AI processing,” said Amichai Long, TI’s senior vice president of embedded processing and DLP® products. “Now, TI is leading the next phase of innovation by integrating TinyEngine NPUs across our microcontroller portfolio, including general-purpose MCUs and high-performance real-time MCUs. By enabling AI across our software, tools, devices, and ecosystem, we are making edge AI accessible and easy to use for every customer and every application.”
“While much of the world has focused on AI acceleration and NPUs on larger SoCs, it turns out that some of the more interesting and far-reaching AI applications can be realized within small chips like microcontrollers,” said Bob O’Donnell, president and principal analyst at TECHnaracy Research. “Edge-based applications of AI acceleration can make consumer devices more intelligent and industrial devices more efficient. Furthermore, if these chips can be combined with software development tools that themselves leverage AI to help build AI capabilities, they can bring the power of AI acceleration to a much broader range of engineers and device designers.”
Advanced intelligence at your fingertips
Consumers are constantly demanding that everyday technology become more intelligent, from fitness wearables to home appliances and electrical systems. However, many engineers believe that AI capabilities are limited to high-end applications, given the high cost, power demands, and coding requirements. TI’s new MSPM0G5187 arm® cortex®The -M0+ MSPM0 MCU represents a fundamental change for embedded designers, allowing them to bring edge AI to a wider range of applications in a simpler, smaller, and more cost-effective manner.
With local computation, the TinyEngine NPU performs the computations required by the neural network in parallel with the primary CPU running the application code. Compared to similar MCUs without accelerators, this hardware acceleration allows you to:
- Minimize flash memory footprint.
- Reduce latency by up to 90x for each AI inference.
- Reduce energy usage per AI inference by more than 120x.
This level of efficiency enables even resource-constrained devices, such as battery-powered portable products, to handle AI workloads. At less than $1 USD in quantities of 1,000, the MSPM0G5187 MCU reduces system and operating costs by providing an affordable alternative to other MCU or processor architectures.
For more information, see the technical article How Edge AI-accelerated Arm Cortex-M0+ MCUs bring more brainpower to electronics.
Real-time control and AI acceleration for multi-motor systems
Motor control applications in consumer electronics, robotics, and industrial systems increasingly require intelligent features such as adaptive control and predictive maintenance, but implementing these features has traditionally required complex multichip designs. TI’s new AM13Ex MCU builds on more than 20 years of motor control leadership through its C2000™ real-time MCU portfolio and is the industry’s first to combine a high-performance Arm Cortex-M33 core, TinyEngine NPU, and advanced real-time control architecture on a single chip.
This level of integration allows designers to simultaneously implement advanced motor control and AI functionality without the use of external components, reducing bill of materials costs by up to 30%. Key enhancements include:
- Ability to maintain accurate real-time control loops for up to four motors while the TinyEngine NPU executes adaptive control algorithms for load sensing and energy optimization.
- An integrated trigonometric accelerator performs calculations 10 times faster than Coordinate Rotation Digital Computer (CORDIC) implementations, resulting in more accurate and responsive motor control performance.
For more information, see the application brief Enabling edge AI-enabled motor control in industrial automation and consumer electronics design.
Easily train, optimize, and deploy AI models
Both MCU families are supported by TI’s CCStudio Edge AI Studio, a free development environment that simplifies model selection, training, and deployment across TI’s embedded processing portfolio. This edge AI toolchain gives engineers complete flexibility to run AI models on TI MCUs through hardware or software implementation. The tool currently has over 60 models and example applications available to help developers start deploying edge AI on any device, with additional tasks and models planned for the future.
TI exhibits at Embedded World 2026
At Embedded World 2026, in Hall 3A, Booth #131, TI will demonstrate how its technology can help engineers accelerate development with AI. Improve performance with edge AI. Deploy AI at the edge across factories, buildings, and vehicles. It also highlights TI’s partner ecosystem, which provides a complete foundation to bring innovative embedded solutions to market faster. For more information, visit ti.com/ew.
PACKAGING, AVAILABILITY AND PRICE
- The production version of the MSPM0G5187 MCU is currently available for purchase on TI.com, and the AM13E23019 MCU is available as a pre-production version. Additional packages and memory variants are expected to be released by the end of 2026.
- Multiple payment and shipping methods are available.
About Texas Instruments
Texas Instruments Incorporated (Nasdaq: TXN) is a global semiconductor company that designs, manufactures and markets analog and embedded processing chips for industrial, automotive, data center, personal electronics, communications equipment and other markets. At our core is a passion for creating a better world by making electronics more affordable through semiconductors. This passion lives on today, with each generation of innovation building on the latest advances, making our technology more reliable, more affordable and lower power, and enabling the use of semiconductors in electronics everywhere. For more information, visit TI.com.
trademark
DLP is a registered trademark of Texas Instruments. TinyEngine, CCStudio, and C2000 are trademarks of Texas Instruments. All other trademarks are the property of their respective owners.
SOURCE Texas Instruments
