{"product_id":"google-coral-m-2-accelerator-a-e-key-ai-accelerator","title":"Google Coral M.2 Accelerator A+E key AI Accelerator","description":"\u003cdiv id=\"product_info_4164908458b618\" class=\"relative\"\u003e\n\u003cdiv class=\"text-24 font-mst-b max1080:text-22 leading-tight py-20 max1080:py-15\"\u003e\u003cbr\u003e\u003c\/div\u003e\n\u003cdiv\u003e\n\u003cdiv class=\"html_content_2981\"\u003e\n\u003cdiv\u003e\n\u003ch2\u003eKey Features\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003ePerforms high-speed ML inferencing: The 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.\u003c\/li\u003e\n\u003cli\u003eWorks with Debian Linux: Integrates with any Debian-based Linux system with a compatible card module slot.\u003c\/li\u003e\n\u003cli\u003eSupports TensorFlow Lite: No need to build models from the ground up. TensorFlow Lite models can be compiled to run on the Edge TPU.\u003c\/li\u003e\n\u003cli\u003eSupports AutoML Vision Edge: Easily build and deploy fast, high-accuracy custom image classification models to your device with \u003ca class=\"mk-link\" href=\"https:\/\/cloud.google.com\/vision\/automl\/docs\/edge-quickstart\" rel=\"noopener noreferrer\" target=\"_blank\"\u003eAutoML Vision Edge\u003c\/a\u003e.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch2\u003eDescription\u003c\/h2\u003e\n\u003cp class=\"body-copy mk-paragraph\"\u003eThe Coral M.2 Accelerator is an M.2 module that brings the Edge TPU coprocessor to existing systems and products.\u003c\/p\u003e\n\u003cp class=\"body-copy mk-paragraph\"\u003eThe Edge TPU is a small ASIC designed by Google that provides high performance ML inferencing with low power requirements: it's 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. This on-device processing reduces latency, increases data privacy, and removes the need for constant high-bandwidth connectivity.\u003c\/p\u003e\n\u003cp class=\"body-copy mk-paragraph\"\u003eThe M.2 Accelerator is a dual-key M.2 card (either A+E or B+M keys), designed to fit any compatible M.2 slot. This form-factor enables easy integration into ARM and x86 platforms so you can add local ML acceleration to products such as embedded platforms, mini-PCs, and industrial gateways.\u003c\/p\u003e\n\u003ch2\u003eSpecification\u003c\/h2\u003e\n\u003cdiv class=\"p_2981_table_wrapper\"\u003e\n\u003ctable class=\"tg p_2981_table\"\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003cth class=\"tg-ecdp\"\u003e\u003cspan\u003ePhysical specifications\u003c\/span\u003e\u003c\/th\u003e\n\u003cth class=\"tg-ecdp\"\u003e\u003c\/th\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"tg-cly1\"\u003eDimensions\u003c\/td\u003e\n\u003ctd class=\"tg-cly1\"\u003eA+E key: 22.00 x 30.00 x 2.35 mm\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"tg-0lax\"\u003eWeight\u003c\/td\u003e\n\u003ctd class=\"tg-0lax\"\u003eA+E key: 3.1 g\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"tg-c8dp\"\u003e\u003cspan\u003eHost interface\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"tg-c8dp\"\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"tg-0lax\"\u003eHardware interface\u003c\/td\u003e\n\u003ctd class=\"tg-0lax\"\u003eM.2 A+E key (M.2-2230-A-E-S3)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"tg-0lax\"\u003eSerial interface\u003c\/td\u003e\n\u003ctd class=\"tg-0lax\"\u003ePCIe Gen2 x1\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"tg-c8dp\"\u003eOperating voltage\u003c\/td\u003e\n\u003ctd class=\"tg-c8dp\"\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"tg-0lax\"\u003eDC supply\u003c\/td\u003e\n\u003ctd class=\"tg-0lax\"\u003e\u003cspan\u003e3.3V +\/- 10 %\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"tg-c8dp\"\u003e\u003cspan\u003eEnvironmental reliability\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"tg-c8dp\"\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"tg-0lax\"\u003eTemperature\u003c\/td\u003e\n\u003ctd class=\"tg-0lax\"\u003e-40 ~ 85° C (storage)\u003cbr\u003e\u003cbr\u003e-20 ~ 70° C (operating)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"tg-0lax\"\u003eRelative humidity\u003c\/td\u003e\n\u003ctd class=\"tg-0lax\"\u003e\u003cspan\u003e0 ~ 100% (non-condensing)\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"tg-c8dp\"\u003e\u003cspan\u003eMechanical reliability\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd class=\"tg-c8dp\"\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"tg-0lax\"\u003eOp-shock\u003c\/td\u003e\n\u003ctd class=\"tg-0lax\"\u003e100 G, 11ms (persistent)\u003cbr\u003e1000 G, 0.5 ms (stress)\u003cbr\u003e1000 G, 1.0 ms (stress)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"tg-0lax\"\u003eOp-vibe (random)\u003c\/td\u003e\n\u003ctd class=\"tg-0lax\"\u003e0.5 Grms, 5 - 500 Hz (persistent)\u003cbr\u003e3 Grms, 5 - 800 Hz (stress)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd class=\"tg-0lax\"\u003eOp-vibe (sinusoidal)\u003c\/td\u003e\n\u003ctd class=\"tg-0lax\"\u003e0.5 Grms, 5 - 500 Hz (persistent)\u003cbr\u003e3 Grms, 5 - 800 Hz (stress)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003c\/div\u003e\n\u003ch2\u003ePinout\u003c\/h2\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/github.com\/SeeedDocument\/Bazaar_Document\/raw\/master\/%E5%BE%AE%E4%BF%A1%E5%9B%BE%E7%89%87_20191231172459.jpg\" alt=\"pin out\" width=\"800\" height=\"894\"\u003e\u003c\/p\u003e\n\u003ch2\u003eDimensions\u003c\/h2\u003e\n\u003cp\u003e\u003cimg src=\"https:\/\/github.com\/SeeedDocument\/Bazaar_Document\/raw\/master\/114992123-size.jpg\" alt=\"dimension\" width=\"800\" height=\"600\"\u003e\u003c\/p\u003e\n\u003ch2\u003ePart List\u003c\/h2\u003e\n\u003cp\u003e1xCoral M.2 Accelerator A+E key\u003c\/p\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cdiv id=\"product_info_f0e13e85e62ce8\" class=\"relative\"\u003e\n\u003cdiv class=\"absolute bottom-full left-0 w-full h-1 p_scroll_into_view_2981\"\u003e\u003cbr\u003e\u003c\/div\u003e\n\u003cdiv class=\"text-24 font-mst-b max1080:text-22 leading-tight py-20 max1080:py-15\"\u003e\n\u003cdiv\u003eDocuments\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cdiv\u003e\n\u003cdiv class=\"html_content_2981\"\u003e\n\u003cdiv class=\"documents_list\"\u003e\n\u003cdiv class=\"doc_item\"\u003e\u003ca href=\"https:\/\/github.com\/SeeedDocument\/Bazaar_Document\/raw\/master\/Coral-M2-datasheet.pdf\" target=\"_blank\"\u003eDatasheet\u003c\/a\u003e\u003c\/div\u003e\n\u003cdiv class=\"doc_item\"\u003e\u003cbr\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e","brand":"Ubo","offers":[{"title":"Default Title","offer_id":54468620288275,"sku":null,"price":75.99,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0726\/6900\/4051\/files\/Screenshot2026-07-21at10.57.00PM.png?v=1784700018","url":"https:\/\/shop.getubo.com\/products\/google-coral-m-2-accelerator-a-e-key-ai-accelerator","provider":"ubo","version":"1.0","type":"link"}