cnx-software.comMar 11

Texas Instruments MSPM0G5187 and AM13Ex MCUs integrate TinyEngine NPU for Edge AI applications

https://fed.brid.gy/r/https://www.cnx-software.com/2026/03/11/texas-instruments-mspm0g5187-and-am13ex-mcus-integrate-tinyengine-npu-for-edge-ai-applications/

Texas Instruments MSPM0G5187 and AM13Ex MCUs integrate TinyEngine NPU for Edge AI applications

Texas Instruments MSPM0G5187 and AM13Ex are two new microcontroller (MCU) families featuring the company's  TinyEngine neural processing unit (NPU) to enable low-latency, high-efficiency Edge AI/Machine Learning inference on the chips. TI claims that the TinyEngine NPU can run AI models with up to 90 times lower latency and more than 120 times lower energy utilization per inference than similar MCUs without an accelerator.  The MSPM0G5187 is a general-purpose, low-power Arm Cortex-M0+ MCU, while the AM13Ex Arm Cortex-M33 microcontroller targets real-time motor control, starting with the AM13E23019 SKU. TI MSPM0G5187 general-purpose Cortex-M0+ MCU Key features and specifications: CPU - Arm Cortex-M0+ @ 80 MHz Memory - 32 KB RAM with ECC Storage - 128 KB flash with ECC, 8 KB data flash with ECC Accelerators TinyEngine NPU for AI/ML delivering up to 2.56GOPS (Giga Operations Per Second) at 80MHz MATHACL math accelerator Peripherals USB - 1x USB 2.0 (12 Mbps) Audio

CNX Software - Embedded Systems News
sayzardFeb 11

Itamar Golan (@ItakGol)

OpenClaw의 'diet mode'로 소개된 PicoClaw: $10 하드웨어에서 <10MB RAM으로 동작하며 메모리 사용을 크게 줄여 비용을 절감하는 소형화·경량화 접근입니다. 소형 임베디드 디바이스에서 구동 가능한 초저자원 AI/런타임 솔루션의 사례로 해석될 수 있습니다.

https://x.com/ItakGol/status/2021363915180081398

#tinyml #edgeai #embedded #openclaw #picoclaw

Itamar Golan 🤓 (@ItakGol) on X

OpenClaw 🤝 diet mode PicoClaw 🦀 $10 hardware <10MB RAM 99% less memory 98% cheaper than a Mac mini

X (formerly Twitter)
sayzardFeb 11

Itamar Golan (@ItakGol)

PicoClaw 발표: OpenClaw 느낌의 초경량 프로젝트로, 약 $10짜리 하드웨어에서 <10MB RAM으로 동작한다고 소개됩니다. 기존 구현 대비 메모리 99% 절감, 비용은 Mac mini 대비 98% 저렴하다고 강조해 엣지/임베디드 환경을 겨냥한 초저자원 AI/실행 플랫폼으로 보입니다.

https://x.com/ItakGol/status/2021363116484022709

#tinyml #edgeai #embedded #openclaw #picoclaw

Itamar Golan 🤓 (@ItakGol) on X

Meet PicoClaw 🦀 OpenClaw vibes, but absurdly small. Runs on $10 hardware with <10MB RAM. 99% less memory. 98% cheaper than a Mac mini.

X (formerly Twitter)
Shawn HymelFeb 11
Full object detection on a #microcontroller in 3.5 ms is quite impressive! Yes, I’m using an #AI accelerator…I’m certainly not doing inference on the CPU in that amount of time 😁 #edgeAI #tinyml #embedded
Doug Whitfield [Minneapolis]Jan 29

So, #TinyML is too small. LLMs are...probably not what I am looking for.

Is there like a GoldieLocksML or something? #ai #ml #machinelearning

Shawn HymelJan 6

Edge AI on microcontrollers (#TinyML) hasn’t had a breakout moment, but it has matured in the past few years. In my latest blog post, I look at some of the major trends of TinyML in the past year as well as speculate on what's coming in 2026.
👇
https://shawnhymel.com/3125/state-of-edge-ai-on-microcontrollers-in-2026/?utm_source=mastodon&utm_medium=social&utm_campaign=general_courses_blog

#EdgeAI #AI #embedded #microcontroller

State of Edge AI on Microcontrollers in 2026 - Shawn Hymel

Over the past couple of years, edge AI on microcontrollers (often called "TinyML") has evolved beyond demos and conference talks. You can now find

Shawn Hymel
cnx-software.comDec 8

Quarky Intellio – A LEGO-compatible AI, Augmented Reality, and IoT learning platform (Crowdfunding)

https://web.brid.gy/r/https://www.cnx-software.com/2025/12/08/quarky-intellio-lego-compatible-ai-augmented-reality-iot-learning-platform/

Show threadGareth HalfacreeNov 19

News from #STMicro as the company updates its #tinyML model zoo - now some 140-models strong, plus with fresh support for #PyTorch after previously pinning its hopes on #tflite.

https://www.hackster.io/news/stmicro-updates-its-tinyml-stm32-model-zoo-now-offers-over-140-ready-to-use-ml-ai-models-47f765aecf5e

(The GitHub release isn't ready yet, for some reason, but STMicro says it's coming "soon.")

#Technology #Microcontroller #Programming #ArtificialIntelligence #News #Hackster

STMicro Updates Its TinyML STM32 Model Zoo, Now Offers Over 140 Ready-to-Use ML, AI Models

The new 4.0.0 release is, the company boasts, the industry's biggest collection of AI and ML models for microcontrollers.

Hackster.io
Shawn HymelOct 28

Running deep learning models on microcontrollers has gained mainstream popularity among silicon vendors and #firmware developers. My latest article examines the state of the #TinyML runtime offerings in 2025.

https://shawnhymel.com/2994/deep-learning-on-microcontrollers-the-state-of-embedded-ml-in-2025/?utm_source=mastodon&utm_medium=social&utm_campaign=general_courses_blog

#microcontroller #embedded #AI #MachineLearning #edgeAI

Deep Learning on Microcontrollers: The State of Embedded ML in 2025 - Shawn Hymel

Edge AI has been gaining traction, and deploying deep learning models on microcontrollers (MCUs) has evolved from a niche experiment to a mainstream

Shawn Hymel
David vonThenenOct 15

#AllThingsOpen 2025 was incredible! 🙌 Huge thanks to everyone who joined my session, "TinyML Meets PyTorch: Deploying AI at the Edge with Python Using ExecuTorch." The live demo energy was 🔥

Grab the slides + code here 👉 https://bit.ly/4mNZL8R

#EdgeAI #TinyML

GitHub - davidvonthenen/2025-all-things-open: All resources (slides, code, etc) for All Things Open 2025: TinyML Meets PyTorch: Deploying AI at the Edge with Python Using ExecuTorch

All resources (slides, code, etc) for All Things Open 2025: TinyML Meets PyTorch: Deploying AI at the Edge with Python Using ExecuTorch - davidvonthenen/2025-all-things-open

GitHub