






Desertcart purchases this item on your behalf and handles shipping, customs, and support to Austria.
🚀 Turbocharge your AI edge with Coral USB Accelerator — speed, simplicity, and smarts in your pocket!
The Seeed Studio Coral USB Accelerator is a compact, energy-efficient Edge TPU coprocessor delivering 4 TOPS of machine learning inference power at just 2 watts. It connects via USB 3.0 Type-C to major platforms including Raspberry Pi, Windows 10, macOS, and Debian Linux, enabling fast, local TensorFlow Lite model execution. Ideal for professionals seeking low-latency, privacy-conscious AI acceleration with easy deployment of custom vision models and seamless Google Cloud compatibility.










| ASIN | B0CDGT75SH |
| Best Sellers Rank | 61,902 in Computers & Accessories ( See Top 100 in Computers & Accessories ) 1,355 in Motherboards |
| Box Contents | / |
| Brand | seeed studio |
| Brand Name | seeed studio |
| CPU Model | Core i7 |
| CPU model | Core i7 |
| CPU speed | 4 GHz |
| Compatible Devices | Raspberry Pi, Intel Celeron J4125 powered X86 Windows/Linux mini PC, Linux systems, Windows 10, MacOS |
| Connectivity technology | USB 3.0 |
| Customer Reviews | 4.0 out of 5 stars 205 Reviews |
| Item Dimensions L x W x H | 13.9L x 10.1W x 3.3H centimetres |
| Manufacturer | seeed studio |
| Manufacturer Part Number | 114991790-FA |
| Memory Storage Capacity | 16 KB |
| Memory storage capacity | 16 KB |
| Model Name | Coral USB Accelerator |
| Model Number | 114991790-FA |
| Model name | Coral USB Accelerator |
| Network Connectivity Technology | USB 3.0 |
| Operating System | Debian Linux, macOS, Windows 10 |
| Processor Brand | ARM |
| Processor Count | 1 |
| Processor Speed | 4 GHz |
| RAM Memory Technology | DDR4 |
| Smart Home Compatibility | Not Smart Home Compatible |
| Total USB Ports | 1 |
| Unit Count | 1.0 count |
M**L
Perfect for frigate
Hard to get one now, works perfectly with proxmox inside lxc running frigate.
R**K
Ninguna de las dos unidades que he comprado funcionan
Dos unidades he pedido, las dos vienen muertas, ni se enciende el led al conectarlo al usb ni lo reconoce ninguno de los 3 pcs en los que he probado, tanto windows como Linux. No se cual es el problema porque ambos venian precintados pero no funcionan. Devueltos.
R**T
Make sure you plug it in the right USB port!
Arrive quite quickly. Plugged it in using supplied cable to USB port on back of a Topton fanless 4 port mini PC (n5105) and passed through USB port from Proxmox to Frigate docker container (running in Docker LXC). Set up camera (Reolink RL-810A) and checked Inference Speed of Coral TPU and it was not good at 29.3 ms. Checked USB port specifications of Topton mini-PC and remembered that the back USB ports are all just USB gen2. Both USB A type ports on front of the Topton are gen3 but both were already in use so plugged Coral cable into a USB-A to USB-C adapter and then plugged adapter into front USB-C port on Topton mini PC. Re-configured USB pass through from Proxmox to container and restarted. Inference Speed dropped to 9.2 ms - should have read the section on using fastest USB port! Added 3 more cameras (one more Reolink RL-810A, one Eufy 2K indoor and one Eufy 2k Pan and Tilt indoor). Inference Speed looks stable at about 8.9 ms (not as good as some reports in frigate forums but still good given Coral is passed through from Proxmox to Docker LXC then Frigate docker container inside that). Coral TPU has been working well for past week and false positives cut down markedly from Eufy cameras (mostly cat detection) compared to native camera app's 'pet' detection while notifications from Frigate NVR via Home Assistant to phone are a few seconds faster than the notifications from the native camera apps but not much in it. Person detection from Reolink itself seems on a par with frigate/coral however but Frigate + Coral is work well with Person, cat, dog, bicycle and motorbike objects while Reolink natively only has Person, Vehicle and Pet. Overall pleased with Coral unit (even though seems expensive) and very pleased with speed of dispatch as well as delivery time from Seeed Studio Store.
M**A
Muito portátil e eficaz.
Produto excelente. Usando o Frigate em meu MiniPC i5, antes do Coral ficava com 85% de consumo de CPU. Com o Coral, caiu para 25~30% de consumo. Recomendo bastante aos que usam Frigate.
P**T
Ne fonctionne pas
Le Google Coral n'est pas reconnu sur Aucun de mes OS, j'ai changé de cable, même combat.
A**A
Funciona como dice, pero lento
El tpu funciona como dice pero lo hace de manera lenta, es decir, dota a la raspberry de la capacidad de procesar informacion como el algoritmo YOLO pero eso mismo hace que el procesamiento disminuya, realembete lo hace pero lo hace lento.
Trustpilot
4 days ago
1 month ago