Your cart is empty.
Your cart is empty.Coral USB Accelerator brings powerful ML (machine learning) inferencing capabilities to existing Linux systems. Featuring the Edge TPU, a small ASIC designed and built by Google, the USB Accelerator provides high performance ML inferencing with a low power cost over a USB 3.0 interface. For example, it can execute state-of-the-art mobile vision models, such as MobileNet v2 at 100+ fps, in a power-efficient manner. This allows fast ML inferencing to embedded AI devices in a power-efficient and privacy-preserving way.
Models are developed in TensorFlow Lite and then compiled to run on the USB Accelerator.
Edge TPU key benefits:
High speed TensorFlow Lite inferencing
Low power
Small footprint
Features
Google Edge TPU ML accelerator coprocessor
USB 3.0 Type-C socket
Supports Debian Linux on host CPU
Models are built using TensorFlow. Fully supports MobileNet and Inception architectures though custom architectures are possible
Compatible with Google Cloud
Specifications
Arm 32-bit Cortex-M0+ Microprocessor (MCU): Up to 32 MHz max 16 KB Flash memory with ECC 2 KB RAM
Connections: USB 3.1 (gen 1) port and cable (SuperSpeed, 5Gb/s transfer speed)
Included cable is USB Type-C to Type-A
Coral, a division of Google, helps build intelligent ideas with a platform for local AI.
Khaled
Reviewed in Saudi Arabia on March 12, 2025
تم محاولة استخدام القطعة وتعريفها على ماك وعلى لينكس ولم يتعرف عليها كل من النظامين والقطعة تصدر حرارة وهي لم تستخدم
Lou
Reviewed in the United States on February 24, 2025
Works!
Glen Eccles
Reviewed in the United States on January 4, 2025
I got it for transcoding, but the camera worked with and without it so not sure I needed it in my situation. Only get it if you find you have problems and don't just assume you need one to record video.
Civodul
Reviewed in France on January 11, 2025
Je l'ai installer sur un Frigate sur home assistant, fonctionne parfaitement et prend en charge une bonne partie des calculs
Yaniv
Reviewed in the United States on April 12, 2025
I’ve been running the Google Coral USB Accelerator as part of my self-hosted Home Assistant and Frigate setup in my home lab, and it’s been a solid upgrade.My cameras stream through it for real-time object detection, and while the AI recognition isn’t perfect, it’s definitely good enough for home security and smart automation triggers.It picks up people, cars, and even the occasional animal (cats 🐱) with decent accuracy, and it’s responsive enough for live notifications or actions.The biggest win is offloading the CPU.Before Coral, my server was getting hammered by the detection workload, especially with multiple cameras running.Now, it’s smooth, CPU usage is way down, and the system feels a lot more stable and responsive. If you’re running Frigate or anything TensorFlow-based in a home setup, the Coral USB is a no-brainer.It’s compact, plug-and-play with a bit of config, and does exactly what it’s meant to.Note that the unit get pretty hot while working, this is normal.
MahatavArora
Reviewed in Canada on September 23, 2024
It is the best and cheapest option for running a YOLO model on my drone. It helps overcome my reliance on the radios (RFD 900s), which can be unreliable after the drone goes beyond the Visual Line Of Sight. It is fast and accurate. The only thing is that you have to run a Docker environment to interact with it or have to use an ancient version on Linux because it hasn't been updated in a while.
Mick
Reviewed in the United Kingdom on November 3, 2024
Simple plug and play, got recognised immediately and definitely speeds up the AI stuff on QNAP, primarily the TS262 as the TS433 has a Neural Processing Unit built in, but i tested it anyway and it worked.I am now tempted to buy a couple more.
John V
Reviewed in the United States on January 26, 2024
This is an amazing and beastly device. If you know you know. It outperforms stacked RTX 1080s like it's child's play.I use this for a Frigate NVR that does detection on 5 camera feeds. Works great and never gets anywhere near capacity. I have it plugged into a rack server with USB 2.0 and it's fine. Probably would be superior with USB 3.Just plug it in and then follow the website. For debian it was a simple repo and package install. That's it. Ready to use. Don't even need to reboot of course yay Linux.If you use it for a Frigate setup maybe keep a light video card like a 2GB Nvidia to use for the movement detection in Frigate (instead of CPU) and use this TPU for object detection. You'll be amazed at the speed increase.
Mike s.
Reviewed in the United States on April 18, 2024
Bad ass little device, Took a load off my i7 processor when running Frigate object detection within Home Assistant on a Dell Optiplex 7050 Tiny
TMG
Reviewed in the United States on August 22, 2023
The Google Coral USB Edge TPU ML Accelerator has been a game-changer for my home security setup. I've integrated it with Frigate to handle image processing from my security cameras, specifically for person detection. This setup, combined with Home Assistant, offers me an added layer of security without the need to lean on cloud services. The device itself is surprisingly compact, which was unexpected. On the downside, while I've noticed the price dropping a bit, it's still higher than what it was a couple of years ago. Nonetheless, for the peace of mind and local processing power it offers, it's been a worthy addition to my tech arsenal.
كوثر القلاف
Reviewed in the United Arab Emirates on March 1, 2023
Good
Persepolis
Reviewed in the United States on October 19, 2023
I had lots of hope for this... it would have been great to have a self contained TPU solution that can provide an assist to classification and detection tasks which I normally do with OpenCV on either a CISC or GPU right now.In comes Coral. The promise of fast tensor operations using a lower power dongle can't be beat.Now comes the bad: first, good luck finding this for the MSRP. Either production is low, or scalpers are having a field day on this. So, from the get-go you're paying 10-20% premium on the device.Next, if you get your hands on it, good luck trying to get it working with anything. Lots of the reviewers like this because they utilize it with Frigate which is cool. A+ for that workload...Now if you want to use it with anything else, there are some examples... and that's where things hit a bumpy road. Check out any of the Github repositories that are posted. Most were posted 3 or 4 years ago and have been untouched since... so trying bringing down an example and getting it to work... Windows examples don't work... WSL doesn't work... a recent version or LTS on Ubuntu... and same thing... nothing works. Good luck getting a response from the support address.So... summary: this thing is great if you have Frigate and need to increase camera counts without buying more cores or GPUs. It may be great if you can get it running on a RPi and do things that are simply not possible, there... but for CV applications... getting this to run will be the long tent pole due to the poorly maintained examples and stale support repositories making it a better move to just skip over this and go with a GPU solution such as a CUDA accelerated OpenCV approach or Deepstacks or anything else for that matter.If anything changes and I get this thing functional, I'll update this review accordingly.
nick
Reviewed in the United States on October 17, 2023
Using this with Frigate NVR running in a docker on Unraid. Easily handles object detection for 8 - 4k Reolink Cameras (using neolink to get access to the 4k feeds over RTSP).CPU use while running hoves around 10%. Without the Coral, CPU use would be over 30%. It also sips power.Highly recommend!
Recommended Products
