Edge AI Devices

Single-board computers, dev kits, and accelerators for running inference outside the datacenter. NVIDIA Jetson, Coral, M.2 TPUs.

2 productsLast reviewed: 2026-05-23

TensorFeed earns a commission from qualifying Amazon purchases. Non-Amazon products are listed without affiliate links. See our affiliate disclosure.

Editor's PickBest for Local LLMNew

NVIDIA

NVIDIA Jetson Orin Nano Super Developer Kit

NVIDIA cut the Orin Nano dev kit to $249 and bumped its AI throughput in the same move, making it the runaway leader in hobbyist edge AI.

·Up to ~67 TOPS sparse INT8 AI performance
·6-core Arm Cortex-A78AE CPU
·8 GB LPDDR5
·M.2 Key M and Key E slots
·USB-C, DisplayPort, gigabit Ethernet

AI use: Local LLM inference at the small-model tier, robotics dev kits, vision pipelines, and the standard reference platform for the entire LeRobot and Isaac ROS stack.

$249

#edge-ai #nvidia #jetson #dev-kit

New

Hailo

Hailo-8 M.2 AI Accelerator

A 26 TOPS M.2 card that drops into a Raspberry Pi 5 or mini PC and quietly outclasses every Edge TPU on the market.

·26 TOPS Hailo-8 processor
·Approximately 2.5 W typical power draw
·M.2 2230, 2242, 2260, 2280 form factors
·PCIe Gen 3 x2 or x4 depending on key
·TensorFlow, TensorFlow Lite, ONNX, Keras, PyTorch

AI use: Edge vision pipelines, real-time object detection, NVR-style smart cameras, and any embedded build that needs more headroom than a Coral TPU but less heat than a Jetson.

$169 to $249

#edge-ai #accelerator #hailo #m2

All gear categories Datacenter chip specs (H100, MI300, TPUs)