Buy anything from 5,000+ international stores. One checkout price. No surprise fees. Join 2M+ shoppers on Desertcart.
Desertcart purchases this item on your behalf and handles shipping, customs, and support to Ireland.
🤖 Turbocharge your AI projects with Google Coral’s USB Edge TPU – where speed meets smarts!
The Google Coral USB Edge TPU is a compact ML accelerator coprocessor featuring a 32 MHz Arm Cortex-M0+ MCU and a USB 3.1 Gen 1 interface delivering 5Gb/s transfer speeds. Designed for embedded single board computers like Raspberry Pi, it supports Debian Linux and TensorFlow models including MobileNet and Inception. Ideal for developers seeking powerful, low-latency AI inferencing on the edge with seamless cloud integration.
| ASIN | B07R53D12W |
| Best Sellers Rank | #45,547 in Computers & Accessories ( See Top 100 in Computers & Accessories ) #362 in Motherboards |
| Brand Name | Google Coral |
| Customer Reviews | 4.4 out of 5 stars 498 Reviews |
| Item Dimensions L x W x H | 7.6L x 5.1W x 2.5H Centimeters |
| Manufacturer | Google Coral |
| Manufacturer Part Number | Coral-USB-Accelerator |
| Memory Storage Capacity | 16 KB |
| Model Number | Coral-USB-Accelerator |
| Network Connectivity Technology | USB |
| Operating System | Linux |
| Processor Brand | ARM |
| Processor Count | 1 |
| Processor Speed | 32 MHz |
| Total USB Ports | 1 |
| UPC | 608614201389 |
A**H
AI at home
Combined with a Raspberry Pi 4 and a custom 3D printed case - as described at the Google MakerAI website. Was able to do the projects as specified. Requires a temperature check every now and then. Too good to be ignored by the serious explorer!
P**Y
Works well with Frigate Home Assistant
Pricey but works well with homeassistant. Using six cameras with frigate in homeassistant installed on a celeron NUC. Good stuff .
B**W
Please do not buy this
This product is more of a relic now and should not be sold online to unsuspecting customers. None of the python packages required to run models on this device are supported or maintained by the manufacturer anymore. I bought this for a hobby project and gave up after several weeks of trying to get it to function.
D**L
Bad seller..
The device is working fine. But the problem is with seller. Seller sold me an used item. I wish if could return it but. Thanks to government for not allowing to import directly. I have to keep the item, which I paid double the original price and used item.
R**T
Works great in frigate and significantly reduces CPU usage
Purchased this device from this seller after a previous order from a different seller arrived DOA. Although slightly more expensive, device arrived quickly and haven't had any issues. Using it with Frigate running in a VM on a NUC 12 Pro with 4 cameras. Device works great and performs as promised, reducing CPU usage in the NUC significantly. Would highly recommend it for this purpose. Getting the device flashed, configured, and passing through to the VM is a little tricky and outside of the scope of this review, but for others who intend to use it that way, search for William Lam's guides on this. They're very detailed, easy to follow, and will get you up and running quickly.
F**E
Genial con frigate
Genial ha bajado el uso de la cpu del pc evitando los cuegues de frigate y minimizando las falsas detecciones
J**N
Super produit
Super produit qui va sur mon mini serveur sur lequel tourne Frigate NVR, il prend toute la charge de détection des objets et soulage le CPU à moindre frais Un peu compliqué à installer sous linux quand on a pas de Debian, je suis sous mageia, mais je laisse 5 étoiles quand même
S**R
Works with debian and Frigate
Recently ditched motioneye for Frigate. Frigate is pretty powerful, but takes a toll on the processor. This "coprocesssor" speeds up detection and recognition. Works well, I would buy again.
ك**ف
Works
Good
Trustpilot
2 months ago
4 days ago