Technical guides for running machine learning on microcontrollers. Hardware specs, framework comparisons, and getting-started tutorials — written for embedded developers.
27 MCU families with Edge AI capability.
i.MX RT1062
NXP
ARM Cortex-M7 @ 600 MHz
1024 KB RAM · 8 MB Flash
20 guides · 4 boards
i.MX RT1064
NXP
ARM Cortex-M7 @ 600 MHz
1024 KB RAM · 4 MB Flash
0 guides · 1 boards
STM32H7
STMicroelectronics
ARM Cortex-M7 @ 480 MHz
1024 KB RAM · 2 MB Flash
21 guides · 22 boards
STM32U5
STMicroelectronics
ARM Cortex-M33 @ 160 MHz
786 KB RAM · 2 MB Flash
20 guides · 2 boards
STM32H5
STMicroelectronics
ARM Cortex-M33 @ 250 MHz
640 KB RAM · 2 MB Flash
0 guides · 1 boards
ESP32
Espressif
Dual-core Xtensa LX6 @ 240 MHz
520 KB RAM · 16 MB Flash
20 guides · 136 boards
ESP32-C6
Espressif
Single-core RISC-V @ 160 MHz
512 KB RAM · 4 MB Flash
20 guides · 5 boards
ESP32-S3
Espressif
Dual-core Xtensa LX7 @ 240 MHz
512 KB RAM · 16 MB Flash
20 guides · 57 boards
GAP8
GreenWaves Technologies
9-core RISC-V (1 FC + 8 Cluster) @ 250 MHz
512 KB RAM · 8 MB Flash
0 guides · 1 boards
i.MX RT1052
NXP
ARM Cortex-M7 @ 600 MHz
512 KB RAM · 8 MB Flash
0 guides · 1 boards
RA6M5
Renesas
ARM Cortex-M33 @ 200 MHz
512 KB RAM · 2 MB Flash
20 guides · 1 boards
STM32F7
STMicroelectronics
ARM Cortex-M7 @ 216 MHz
512 KB RAM · 2 MB Flash
20 guides · 9 boards
ESP32-C3
Espressif
Single-core RISC-V @ 160 MHz
400 KB RAM · 4 MB Flash
17 guides · 16 boards
ESP32-S2
Espressif
Single-core Xtensa LX7 @ 240 MHz
320 KB RAM · 4 MB Flash
0 guides · 28 boards
LPC55xx
NXP
Dual-core ARM Cortex-M33 @ 150 MHz
320 KB RAM · 640 KB Flash
0 guides · 1 boards
EFR32MG
Silicon Labs
ARM Cortex-M4F @ 40 MHz
256 KB RAM · 1 MB Flash
0 guides · 1 boards
nRF52840
Nordic Semiconductor
ARM Cortex-M4F @ 64 MHz
256 KB RAM · 1 MB Flash
19 guides · 22 boards
SAMD51
Microchip
ARM Cortex-M4F @ 120 MHz
256 KB RAM · 1 MB Flash
0 guides · 18 boards
SAME51
Microchip
ARM Cortex-M4F @ 120 MHz
256 KB RAM · 1 MB Flash
0 guides · 1 boards
STM32L5
STMicroelectronics
ARM Cortex-M33 @ 110 MHz
256 KB RAM · 512 KB Flash
0 guides · 1 boards
STM32WB
STMicroelectronics
ARM Cortex-M4F @ 64 MHz + Cortex-M0+ @ 32 MHz
256 KB RAM · 1 MB Flash
0 guides · 2 boards
STM32F4
STMicroelectronics
ARM Cortex-M4F @ 168 MHz
192 KB RAM · 1 MB Flash
16 guides · 105 boards
nRF52833
Nordic Semiconductor
ARM Cortex-M4F @ 64 MHz
128 KB RAM · 512 KB Flash
10 guides · 4 boards
STM32G4
STMicroelectronics
ARM Cortex-M4F @ 170 MHz
128 KB RAM · 512 KB Flash
0 guides · 7 boards
STM32L4
STMicroelectronics
ARM Cortex-M4F @ 80 MHz
128 KB RAM · 1 MB Flash
11 guides · 22 boards
STM32F3
STMicroelectronics
ARM Cortex-M4F @ 72 MHz
80 KB RAM · 512 KB Flash
0 guides · 13 boards
nRF52832
Nordic Semiconductor
ARM Cortex-M4F @ 64 MHz
64 KB RAM · 512 KB Flash
0 guides · 19 boards
Activity Recognition
Classifying human physical activities such as walking, running, sitting, cycling, and climbing stairs from wearable IMU …
0 guides
Air Quality Anomaly Detection
Detecting unusual patterns in gas sensor readings to identify air quality hazards, chemical leaks, or ventilation failur…
0 guides
Anomaly Detection
Detecting unusual patterns in sensor data using lightweight autoencoders or statistical models. Learns normal operating …
27 guides
Baby Cry Detection
Detecting infant crying from ambient audio for smart nursery monitors. Privacy-preserving since audio is classified on-d…
0 guides
Barcode and QR Code Reading
Detecting and decoding barcodes or QR codes from camera images on-device. Modern ML-based approaches handle damaged, par…
0 guides
Bearing Fault Detection
Specialized predictive maintenance focused on detecting early-stage bearing failures in rotating machinery. Analyzes hig…
0 guides
Crop Disease Detection
Classifying plant leaf images to identify diseases, nutrient deficiencies, or pest damage. Deployed on battery-powered d…
0 guides
Fall Detection
Detecting fall events from IMU accelerometer and gyroscope data in real time. Classifies motion patterns to distinguish …
26 guides
Gesture Recognition
Classifying hand or body gestures from IMU (accelerometer + gyroscope) data. Models process short windows of motion data…
27 guides
Glass Break Detection
Detecting the specific acoustic signature of breaking glass for security applications. Uses mel-spectrogram features fed…
0 guides
Image Classification
Classifying entire images into predefined categories without localization. The model outputs a single class label per fr…
22 guides
License Plate Recognition
Detecting and reading license plates from camera images at the edge. Combines object detection for plate localization wi…
0 guides
Machine Sound Monitoring
Classifying machinery sounds to detect abnormal operation such as bearing noise, belt squeal, pump cavitation, or motor …
0 guides
Object Detection
Identifying and localizing objects in camera images on-device. Typical models include quantized MobileNet-SSD or YOLO-ba…
16 guides
People Counting
Counting the number of people entering or occupying a space using on-device vision. Uses lightweight detection or classi…
18 guides
Power Quality Monitoring
Monitoring electrical current and voltage waveforms to detect anomalies in power distribution systems. Identifies power …
0 guides
Predictive Maintenance
Monitoring machinery vibration, temperature, and current patterns to detect anomalies before failures occur. Models anal…
27 guides
Pump Cavitation Detection
Detecting cavitation in pumps and hydraulic systems by analyzing vibration and acoustic patterns simultaneously. Cavitat…
0 guides
Scene Classification
Classifying entire camera frames into scene categories such as indoor vs outdoor, day vs night, crowded vs empty, or roo…
0 guides
Sound Classification
Classifying environmental sounds into categories such as glass breaking, dog barking, machinery noise, sirens, or alarms…
26 guides
Speaker Identification
Identifying who is speaking from voice characteristics without recognizing what is said. Extracts speaker embeddings fro…
0 guides
Vibration Anomaly Detection
Detecting abnormal vibration patterns in rotating machinery such as motors, pumps, fans, and compressors. Learns normal …
0 guides
Visual Defect Detection
Identifying manufacturing defects such as cracks, scratches, missing components, or surface irregularities on production…
0 guides
Voice Command Recognition
Recognizing a vocabulary of 10 to 50 spoken commands on-device without cloud connectivity. Extends beyond single-keyword…
0 guides
Voice Recognition
On-device keyword spotting and voice command recognition without cloud connectivity. Typical models use DS-CNN or depthw…
23 guides
Wake Word Detection
Always-on keyword spotting that listens for a specific activation phrase. Ultra-low-power operation is critical since th…
0 guides
Wildlife Monitoring
Detecting and classifying wildlife species from camera trap images on-device. Reduces data transmission by only sending …
22 guides
Compare ESP32-S3, STM32H7, ESP32-C3, and Arduino Nano 33 BLE for on-device ML. Specs, benchmarks, and use-case recommendations.
What AI agents mean on microcontrollers: sensor-inference-action loops, multi-model pipelines, and autonomous decision logic on ESP32 and STM32.
Step-by-step guide to deploying machine learning models on ESP32, STM32, and Arduino MCUs using TensorFlow Lite Micro and Edge Impulse.
How manufacturers deploy edge AI for quality control, predictive maintenance, and energy monitoring. MCU-based solutions without cloud dependency.
Compare edge AI and cloud AI across latency, cost, privacy, and power. Learn when to process on-device and when cloud inference is the better choice.
Compare ESP32 and STM32 for edge AI. Architecture, ML performance, tooling, connectivity, and cost analysis for embedded ML projects.
Step-by-step guide to running TFLite Micro (LiteRT) on ESP32 with ESP-IDF. Tensor arena, operator registration, and C inference code included.
Deploy edge AI for predictive maintenance. Vibration analysis, anomaly detection, and ROI calculation for MCU-based monitoring on factory equipment.
Learn TinyML from scratch. Set up your first machine learning project on a microcontroller with ESP32, Arduino, or STM32 using TFLite Micro or Edge Impulse.
Edge AI orchestration coordinates ML models, sensors, and actions on microcontrollers. Learn how workflow-based AI deployment replaces monolithic firmware.
The MCU Compatibility Checker matches your use case to the best hardware — with specs, scores, and technical reasoning.
Open MCU CheckerForestHub compiles visual AI workflows to C code for your microcontroller. Pick your hardware, build your pipeline, deploy in minutes.
Get Started Free