A development board to quickly prototype on-device ML products.
The Google Coral Dev Board Mini is a single-board computer that provides fast machine learning (ML) inferencing in a small form factor. It's primarily designed as an evaluation device for the Accelerator Module (a surface-mounted module that provides the Edge TPU), but it's also a fully-functional embedded system you can use for various on-device ML projects.
The on-board Edge TPU coprocessor is capable of performing 4 trillion operations (tera-operations) per second (TOPS), using 0.5 watts for each TOPS (2 TOPS per watt). For example, it can execute state-of-the-art mobile vision models such as MobileNet v2 at almost 400 FPS, in a power efficient manner. See more performance benchmarks.
A single-board computer with SoC + ML + wireless connectivity, all on the board running a derivative of Debian Linux we call Mendel, so you can run your favorite Linux tools with this board.
No need to build models from the ground up. TensorFlow Lite models can be compiled to run on the Edge TPU.
Easily build and deploy fast, high-accuracy custom image classification models to your device with AutoML Vision Edge.
|CPU||MediaTek 8167s SoC (Quad-core Arm Cortex-A35)|
|GPU||IMG PowerVR GE8300 (integrated in SoC)|
|ML accelerator||Google Edge TPU coprocessor:
4 TOPS (int8); 2 TOPS per watt
|RAM||2 GB LPDDR3|
|Flash memory||8 GB eMMC|
|Wireless||Wi-Fi 5 (802.11a/b/g/n/ac); Bluetooth 5.0|
|Audio/video||3.5mm audio jack; digital PDM microphone; 2.54mm 2-pin speaker terminal; micro HDMI (1.4); 24-pin FFC connector for MIPI-CSI2 camera (4-lane); 24-pin FFC connector for MIPI-DSI display (4-lane)|
|Input/output||40-pin GPIO header; 2x USB Type-C (USB 2.0)|
- Model compatibility on the Edge TPU
- Edge TPU inferencing overview
- Run multiple models with multiple Edge TPUs
- Pipeline a model with multiple Edge TPUs
Payment & Accreditations
Your payment information is processed securely. We do not store credit card details nor have access to your credit card information.