{"product_id":"google-coral-m2-accelerator-ae-key","title":"Google Coral M.2 Accelerator A+E Key","description":"\u003cp\u003eThe Coral M.2 Accelerator is an M.2 module that brings the Edge TPU coprocessor to existing systems and products with an available card module slot. Integrate the Edge TPU into legacy and new systems using an M.2 A+E key interface.\u003c\/p\u003e\n\u003cp\u003eAlso available in M.2 B+M key.\u003c\/p\u003e\n\u003ch3\u003ePerforms high-speed ML inferencing\u003c\/h3\u003e\n\u003cp\u003eThe 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 400 FPS, in a power-efficient manner. See more performance benchmarks.\u003c\/p\u003e\n\u003ch3\u003eWorks with Debian Linux and Windows\u003c\/h3\u003e\n\u003cp\u003eIntegrates with any Debian-based Linux or Windows 10 system with a compatible card module slot.\u003c\/p\u003e\n\u003ch3\u003eSupports TensorFlow Lite\u003c\/h3\u003e\n\u003cp\u003eNo need to build models from the ground up. TensorFlow Lite models can be compiled to run on the Edge TPU.\u003c\/p\u003e\n\u003ch2\u003eSpecifications\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eML accelerator: Google Edge TPU coprocessor: 4 TOPS (int8); 2 TOPS per watt\u003c\/li\u003e\n\u003cli\u003eConnector: M.2 (A+E key)\u003c\/li\u003e\n\u003cli\u003eDimensions: 22 mm x 30 mm (\u003cspan\u003eM.2-2230-A-E-S3\u003c\/span\u003e)\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2\u003eResources\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eDatasheet\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cstrong\u003eApplication notes\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eGet started with the M.2 or PCIe Accelerator\u003c\/li\u003e\n\u003cli\u003eManage the PCIe module temperature\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cstrong\u003eSoftware Guides\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eModel compatibility on the Edge TPU\u003c\/li\u003e\n\u003cli\u003eEdge TPU inferencing overview\u003c\/li\u003e\n\u003cli\u003eRun multiple models with multiple Edge TPUs\u003c\/li\u003e\n\u003cli\u003ePipeline a model with multiple Edge TPUs\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cstrong\u003eAPI references\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003ePyCoral API (Python)\u003c\/li\u003e\n\u003cli\u003eLibcoral API (C++)\u003c\/li\u003e\n\u003cli\u003eLibedgetpu API (C++)\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cstrong\u003eDownloads\u003c\/strong\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eEdge TPU compiler\u003c\/li\u003e\n\u003cli\u003ePre-compiled models\u003c\/li\u003e\n\u003cli\u003eAll software downloads\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"Google","offers":[{"title":"Default Title","offer_id":48624237379802,"sku":"jfv1789687637278","price":36.38,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0824\/8318\/3834\/files\/google-coral-m2-accelerator-ae-key_1.jpg?v=1789687643","url":"https:\/\/memoryfoamwear.shop\/products\/google-coral-m2-accelerator-ae-key","provider":"My Store","version":"1.0","type":"link"}