{"product_id":"google-coral-system-on-module-som-1gb-discontinued","title":"Google Coral System-on-Module (SoM) - 1GB [Discontinued]","description":"\u003cp\u003e\u003cstrong\u003eA fully-integrated system for accelerated ML applications (includes CPU, GPU, Edge TPU, Wi-Fi, Bluetooth, and Secure Element), in a 40mm x 48mm pluggable module.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp class=\"body-copy mk-paragraph\"\u003eThe Google Coral System-on-Module (SoM) is a fully-integrated system that helps you build embedded devices that demand fast machine learning (ML) inferencing. It contains NXP's iMX 8M system-on-chip (SoC), eMMC memory, LPDDR4 RAM, Wi-Fi, and Bluetooth, but its unique power comes from Google's Edge TPU coprocessor for high-speed machine learning inferencing.\u003c\/p\u003e\n\u003ch3 class=\"small-headline mk-heading\" id=\"provides-a-complete-system\"\u003eProvides a complete system\u003ci class=\"material-icons icon-link\"\u003e\u003c\/i\u003e\n\u003c\/h3\u003e\n\u003cp class=\"body-copy mk-paragraph\"\u003eThe Coral SoM is a fully-integrated Linux system that includes NXP's iMX8M system-on-chip (SoC), eMMC memory, LPDDR4 RAM, Wi-Fi, and Bluetooth, and the Edge TPU coprocessor for ML acceleration. It runs a derivative of Debian Linux we call Mendel.\u003c\/p\u003e\n\u003ch3 class=\"small-headline mk-heading\" id=\"performs-high-speed-ml-inferencing\"\u003ePerforms high-speed ML inferencing\u003ci class=\"material-icons icon-link\"\u003e\u003c\/i\u003e\n\u003c\/h3\u003e\n\u003cp class=\"body-copy mk-paragraph\"\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 almost 400 FPS, in a power-efficient manner.\u003cspan\u003e \u003c\/span\u003eSee more performance benchmarks.\u003c\/p\u003e\n\u003ch3 class=\"small-headline mk-heading\" id=\"integrates-with-your-custom-hardware\"\u003eIntegrates with your custom hardware\u003ci class=\"material-icons icon-link\"\u003e\u003c\/i\u003e\n\u003c\/h3\u003e\n\u003cp class=\"body-copy mk-paragraph\"\u003eThe SoM connects to your own baseboard hardware with three 100-pin connectors.\u003c\/p\u003e\n\u003ch3 class=\"small-headline mk-heading\" id=\"supports-tensorflow-lite\"\u003eSupports TensorFlow Lite\u003ci class=\"material-icons icon-link\"\u003e\u003c\/i\u003e\n\u003c\/h3\u003e\n\u003cp class=\"body-copy mk-paragraph\"\u003eNo need to build models from the ground up.\u003cspan\u003e \u003c\/span\u003eTensorFlow Lite\u003cspan\u003e \u003c\/span\u003emodels can be compiled to run on the Edge TPU.\u003c\/p\u003e\n\u003ch3 class=\"small-headline mk-heading\" id=\"supports-automl-vision-edge\"\u003eSupports AutoML Vision Edge\u003ci class=\"material-icons icon-link\"\u003e\u003c\/i\u003e\n\u003c\/h3\u003e\n\u003cp class=\"body-copy mk-paragraph\"\u003eEasily build and deploy fast, high-accuracy custom image classification models to your device with\u003cspan\u003e \u003c\/span\u003eAutoML Vision Edge.\u003c\/p\u003e\n\u003cp class=\"body-copy mk-paragraph\"\u003eAlso available with a baseboard as part of the\u003cspan\u003e \u003c\/span\u003eCoral Dev Board.\u003c\/p\u003e\n\u003ch2 class=\"body-copy mk-paragraph\"\u003eSpecifications\u003c\/h2\u003e\n\u003ctable style=\"width: 534px;\" class=\"table-group-table\"\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd class=\"bold col-mobile-6 col-tablet-8 col-small-desktop-7 col-desktop-8\" style=\"width: 149.734px;\"\u003eCPU\u003c\/td\u003e\n\u003ctd style=\"width: 356.266px;\"\u003eNXP i.MX 8M SoC (quad Cortex-A53, Cortex-M4F)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"bold col-mobile-6 col-tablet-8 col-small-desktop-7 col-desktop-8\" style=\"width: 149.734px;\"\u003eGPU\u003c\/td\u003e\n\u003ctd style=\"width: 356.266px;\"\u003eIntegrated GC7000 Lite Graphics\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"bold col-mobile-6 col-tablet-8 col-small-desktop-7 col-desktop-8\" style=\"width: 149.734px;\"\u003eML accelerator\u003c\/td\u003e\n\u003ctd style=\"width: 356.266px;\"\u003eGoogle Edge TPU coprocessor:\u003cbr\u003e4 TOPS (int8); 2 TOPS per watt\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"bold col-mobile-6 col-tablet-8 col-small-desktop-7 col-desktop-8\" style=\"width: 149.734px;\"\u003eRAM\u003c\/td\u003e\n\u003ctd style=\"width: 356.266px;\"\u003e1 GB LPDDR4\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"bold col-mobile-6 col-tablet-8 col-small-desktop-7 col-desktop-8\" style=\"width: 149.734px;\"\u003eFlash memory\u003c\/td\u003e\n\u003ctd style=\"width: 356.266px;\"\u003e8 GB eMMC\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"bold col-mobile-6 col-tablet-8 col-small-desktop-7 col-desktop-8\" style=\"width: 149.734px;\"\u003eWireless\u003c\/td\u003e\n\u003ctd style=\"width: 356.266px;\"\u003eWi-Fi 2x2 MIMO (802.11b\/g\/n\/ac 2.4\/5GHz) and Bluetooth 4.2\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"bold col-mobile-6 col-tablet-8 col-small-desktop-7 col-desktop-8\" style=\"width: 149.734px;\"\u003eDimensions\u003c\/td\u003e\n\u003ctd style=\"width: 356.266px;\"\u003e48mm x 40mm x 5mm\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003ch2 class=\"body-copy mk-paragraph\"\u003eResources\u003c\/h2\u003e\n\u003cdiv class=\"row\"\u003e\n\u003cdiv class=\"col-mobile-14 col-mobile-offset-1 col-tablet-30 col-small-desktop-28 col-desktop-28 col-tablet-offset-1 col-small-desktop-offset-2 col-desktop-offset-2 text-align-left module-text-group-copy\"\u003e\n\u003cdiv class=\"markdown-container\"\u003e\n\u003cp class=\"small-headline mk-heading\" id=\"datasheet\"\u003e\u003cstrong\u003eDatasheet\u003c\/strong\u003e\u003ci class=\"material-icons icon-link\"\u003e\u003c\/i\u003e\u003c\/p\u003e\n\u003cul class=\"mk-list\"\u003e\n\u003cli class=\"mk-list-item body-copy\"\u003eSystem-on-Module datasheet\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp class=\"small-headline mk-heading\" id=\"application-notes\"\u003e\u003cstrong\u003eApplication notes\u003ci class=\"material-icons icon-link\"\u003e\u003c\/i\u003e \u003c\/strong\u003e\u003c\/p\u003e\n\u003cul class=\"mk-list\"\u003e\n\u003cli class=\"mk-list-item body-copy\"\u003e\n\u003cp\u003eGet started with the System-on-Module\u003c\/p\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"module-text-group-modules\"\u003e\n\u003csection class=\"module show\" data-module-type=\"text\"\u003e\n\u003cdiv class=\"grid-container\"\u003e\n\u003cdiv class=\"row\"\u003e\n\u003cdiv class=\"col-mobile-14 col-mobile-offset-1 col-tablet-30 col-small-desktop-28 col-desktop-28 col-tablet-offset-1 col-small-desktop-offset-2 col-desktop-offset-2 text-align-left module-text-copy\"\u003e\n\u003cdiv class=\"markdown-container\"\u003e\n\u003cp class=\"small-headline mk-heading\" id=\"software-guides\"\u003e\u003cstrong\u003eSoftware guides\u003ci class=\"material-icons icon-link\"\u003e\u003c\/i\u003e \u003c\/strong\u003e\u003c\/p\u003e\n\u003cul class=\"mk-list\"\u003e\n\u003cli class=\"mk-list-item body-copy\"\u003e\n\u003cp\u003eModel compatibility on the Edge TPU\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli class=\"mk-list-item body-copy\"\u003e\n\u003cp\u003eEdge TPU inferencing overview\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli class=\"mk-list-item body-copy\"\u003e\n\u003cp\u003eRun multiple models with multiple Edge TPUs\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli class=\"mk-list-item body-copy\"\u003e\n\u003cp\u003ePipeline a model with multiple Edge TPUs\u003c\/p\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp class=\"small-headline mk-heading\" id=\"api-references\"\u003e\u003cstrong\u003eAPI references\u003ci class=\"material-icons icon-link\"\u003e\u003c\/i\u003e \u003c\/strong\u003e\u003c\/p\u003e\n\u003cul class=\"mk-list\"\u003e\n\u003cli class=\"mk-list-item body-copy\"\u003e\n\u003cp\u003ePyCoral API (Python)\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli class=\"mk-list-item body-copy\"\u003e\n\u003cp\u003eLibcoral API (C++)\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli class=\"mk-list-item body-copy\"\u003e\n\u003cp\u003eLibedgetpu API (C++)\u003c\/p\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp class=\"small-headline mk-heading\" id=\"downloads\"\u003e\u003cstrong\u003eDownloads\u003c\/strong\u003e\u003ci class=\"material-icons icon-link\"\u003e\u003c\/i\u003e\u003c\/p\u003e\n\u003cul class=\"mk-list\"\u003e\n\u003cli class=\"mk-list-item body-copy\"\u003e\n\u003cp\u003eEdge TPU compiler\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli class=\"mk-list-item body-copy\"\u003e\n\u003cp\u003ePre-compiled models\u003c\/p\u003e\n\u003c\/li\u003e\n\u003cli class=\"mk-list-item body-copy\"\u003e\n\u003cp\u003eAll software downloads\u003c\/p\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/section\u003e\n\u003c\/div\u003e","brand":"Google","offers":[{"title":"Default Title","offer_id":53697550516500,"sku":"yds1787258209505","price":71.04,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0946\/9486\/7220\/files\/google-coral-system-on-module-som---1gb-discontinued_1.jpg?v=1787258214","url":"https:\/\/regalwearstore.shop\/products\/google-coral-system-on-module-som-1gb-discontinued","provider":"My Store","version":"1.0","type":"link"}