Start HereBrowseCompareUBDS StandardContribute
// ai_edge

AI & Edge Computing

On-device inference, computer vision, and ML acceleration. Run models at the edge without cloud dependencies — from Coral TPUs to Jetson GPUs to Kendryte NPUs.

3boards
·
1beginner
·
1intermediate
·
1advanced
// featured_boards

Hand-picked for AI

The boards we'd recommend first if someone walked up and said “I want to build a ai & edge computingproject.”

Espressif ESP32-S3-DevKitC-1-N8 (8 MB QD, No PSRAM)
Espressif Systems
Espressif ESP32-S3-DevKitC-1-N8 (8 MB QD, No PSRAM)
MCU
intermediate
NXP i.MX RT1060 Evaluation Kit
NXP Semiconductors
NXP i.MX RT1060 Evaluation Kit
MCU
advanced
ST Nucleo H743ZI
STMicroelectronics
ST Nucleo H743ZI
MCU
intermediate
// ecosystem_overview

What UBDS tracks for AI boards

Edge-AI boards ship with one of a half-dozen accelerator families — each with its own quantization story, framework support, and thermal envelope. UBDS catalogs accelerator name, TOPS rating, supported runtimes, and the exact model formats that will actually run.

// accelerators
Edge TPU · NPU · GPU · DLA · NNA · Hailo
// runtimes
TensorFlow Lite · ONNX · PyTorch Mobile · TensorRT · OpenVINO
// model_formats
INT8 · FP16 · SavedModel · TFLite · ONNX
// latest_activity

Recently added & updated

UPDATED2026-06-04Adafruit Industries Adafruit Feather M0MCU-653UPDATED2026-06-04Adafruit Industries Adafruit ItsyBitsy M4 ExpressMCU-673UPDATED2026-06-04Adafruit Industries Adafruit Motor/Stepper/Servo Shield v2.3EXP-225
// related_domains

Also worth a look