Texas Instruments Released MSPM0G5187 Mixed-Signal MCU
The new microcontroller integrates an Arm Cortex-M0+ CPU with a dedicated NPU for edge-AI processing.
Updated on Sept. 30, 2026 in Semiconductors
Live Poll
Do you believe integrating AI capabilities into everyday household electronics makes your life better?
Texas Instruments has released the MSPM0G5187, a mixed-signal microcontroller featuring an integrated neural processing unit (NPU) for edge-AI inference. The device is now available for purchase through Mouser Electronics.
Why it matters
The integration of a specialized NPU allows low-power microcontrollers to perform machine-learning inference autonomously from the main CPU, accelerating data-heavy tasks at the network edge. This development provides engineers with a dedicated hardware path for AI processing in resource-constrained embedded systems.
The MSPM0G5187 runs at a maximum frequency of 80 MHz and features 128 KB of flash memory along with 32 KB of SRAM. Its integrated NPU achieves a performance throughput of 2.56 GOPS.
The players
Texas Instruments
A global semiconductor firm specializing in analog and embedded processing chips for industrial, automotive, and personal electronics markets.
Mouser Electronics
A global distributor of semiconductors and electronic components that serves as a primary retail channel for hardware development parts.
The details
The device centers on an Arm Cortex-M0+ CPU paired with an NPU that operates autonomously to handle machine-learning inference. The flash memory is organized into two banks with address-swap support, a mechanism that allows the system to update firmware in the field without interrupting operations. I/O includes a 12-bit analog-to-digital converter (ADC) capable of 1.6-MSPS (million samples per second) and four configurable UNICOMM serial interface modules.
Timeline
September 30, 2026: The MSPM0G5187 was released and made available for purchase.
The Tech Race
This release follows the industry trend of shifting machine-learning workloads from the cloud to the extreme edge by integrating specialized NPUs directly into low-power MCUs. It directly competes with other silicon vendors aiming to provide dedicated AI inference capabilities in the sub-100 MHz performance tier.
Developers can now purchase the MSPM0G5187 through current distribution channels to begin integrating edge-AI into new embedded designs. The platform utilizes standard Arm-based workflows, meaning existing firmware development processes remain compatible while gaining the new NPU capability.
The takeaway
The move to integrate NPUs into low-cost MCUs indicates that edge-AI will increasingly become a standard feature for basic sensors and controllers. Watch for future benchmarks detailing real-world inference power efficiency compared to traditional CPU-based processing.
Further reading
For broader trends in chip design, visit the Semiconductors section.
More information
Purchase units or access technical documentation via the Mouser Electronics product store.
Source note: This article includes information reported by Military & Aerospace Electronics.
Live Poll
Do you believe integrating AI capabilities into everyday household electronics makes your life better?
