Coral M.2 Accelerator with Dual Edge TPU …

So far so good running YOLO on Frigate NVR. Detections are quick installation was easy using the correct adapter.

Make sure you have compatible hardware. I bought this plus and adapter to use in my older SSSE3 capable motherboard, but the aging Google drivers, the compiled versions, only support SSE4.1 and up. Ended up compiling special drivers for Frigate and got it working. Dropped the CPU utilization to 30% for AI detection. BTW, this setup only supports one half of the TPU, since this is a dual core, but thats no problem for me and I knew that when buying. Learned a lot about "slots" during this buying process. I used this adapter "HLT M.2 (NGFF) to mPCIe (PCIe+USB) Adapter" to make it work in my Wifi card slot.

Pay attention that it's an E-key and NOT M-Key; thus, you need to buy an adapter. I assmed that every M.2 should work with my QNAP NAS but I was wrong....big time! M.2 is a general concept and you need to know in adavnce what Key is suitable for your system. Ordered the adapter and still waiting to test this product. Please do ur homework first and see if this the right choice for you. Better off to buy the M.2 M-Key and pay a bit more than this useless E-Key that NO one is using in 2026!

Works well with blueiris but you definitely want to get pci base card to make it work, even though computer had wifi card socket , this one didn't work with it , I had to order compatible adapter.

This Coral M.2 Accelerator works flawlessly. I added it to my server specifically for AI object detection with Frigate, and the performance jump is incredible. The dual Edge TPU handles real-time detection smoothly, runs cool, and stays completely stable. Setup was quick, and it integrated with my system without any issues. If you’re using Frigate or need solid hardware acceleration for machine learning tasks, this is absolutely worth it.

As others have pointed out, the "Coral" device itself is great; however you need to be extra careful which M.2 version you get. I had to return these for the M.2 A+E key version as I removed a M.2 WiFi card and wanted to replace it with a M.2 Coral. THIS version of the device will likely NOT work with your motherboard, look for the A+E key version instead. That unit works good on Linux (had to manually build a DKMS module for it to work on Ubuntu 24.04) and Frigate integration is pretty straight forward. Frigate shows an inference speed of 7.5ms and the device runs at 51°C.

Difficult to use. You have to have. Avery specific and rare M.2 slot that most motherboards won't have. Would have been Greta to have included the adapters you can find online for these to make them use able on more motherboards.

Used this to integrate first into a blue iris camera system for object detection. I later switched to frigate and again, it's worked without issue. Excellent quality product and fits my needs perfectly. Low power ai object recognition.

not working at all

Works wonders!

TPU détecté, mais pour ce qui est du contenu du colis, il n'y aura que le tpu en lui-même. Pas de dissipateur thermique, manuel d'utilisation comme promis dans la description! J'ai posé la question au vendeur, mais pas de retour! Cordialement.

Viene sin caja, metido en una bolsa de plástico de burbujas, y esta a su vez en otra. Un producto muy pequeño, delicado y sin caja del fabricante. Parece de segunda mano o de baja calidad. Aún no la he instalado. Espero funcione. Muy mala presentación para ser tan cara.

Shoved this in my qnap to speed up the QuMagie AI. Works great shows up as 2 TPU's but had to buy a special multiplexing adapter to an m.2 slot and then also get a m.2 to pci slot card. But that's as much to do with the qnap as the card itself.