{"title":"PCIe","description":"","products":[{"product_id":"metis-pcie-card-unmatched-performance-for-edge-ai-applications","title":"Metis 1-chip PCIe AI Accelerator Card","description":"\u003cp class=\"MsoNormal\"\u003e\u003cspan style=\"mso-ansi-language: EN-US;\" lang=\"EN-US\"\u003e\u003cstrong\u003eAxelera\u003cmeta charset=\"utf-8\"\u003e® AI’s PCIe card\u003c\/strong\u003e, powered by a Quad-core\u003cstrong\u003e Metis\u003cmeta charset=\"utf-8\"\u003e® AIPU,\u003c\/strong\u003e offers the highest performance inference acceleration on the market, combining ease of use, power efficiency, and scalability.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp class=\"MsoNormal\"\u003e\u003cspan style=\"mso-ansi-language: EN-US;\" lang=\"EN-US\"\u003e\u003cstrong\u003eNow available\u003c\/strong\u003e in two configurations:\u003c\/span\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli class=\"MsoNormal\"\u003e\u003cspan style=\"mso-ansi-language: EN-US;\" lang=\"EN-US\"\u003e4 GB memory\u003c\/span\u003e\u003c\/li\u003e\n\u003cli class=\"MsoNormal\"\u003e\u003cspan style=\"mso-ansi-language: EN-US;\" lang=\"EN-US\"\u003e16 GB memory*\u003c\/span\u003e\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp class=\"MsoNormal\"\u003e\u003cspan style=\"mso-ansi-language: EN-US;\" lang=\"EN-US\"\u003e*Please \u003ca title=\"Axelera Contact Form\" href=\"https:\/\/axelera.ai\/contact-us\"\u003econtact us\u003c\/a\u003e for additional memory configuration.\u003c\/span\u003e\u003cb\u003e\u003cspan style=\"mso-ansi-language: EN-US;\" lang=\"EN-US\"\u003e\u003c\/span\u003e\u003c\/b\u003e\u003c\/p\u003e\n\u003cp class=\"MsoNormal\"\u003e\u003cb\u003e\u003cspan style=\"mso-ansi-language: EN-US;\" lang=\"EN-US\"\u003eKey Benefits:\u003c\/span\u003e\u003c\/b\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli class=\"MsoNormal\"\u003e\u003cspan style=\"mso-ansi-language: EN-GB;\" lang=\"EN-GB\"\u003eThe highest-performance \u003cstrong\u003eAI-accelerator PCIe \u003c\/strong\u003ecard in the market for edge AI applications. Powered by a quad-core Metis AIPU.\u003c\/span\u003e\u003c\/li\u003e\n\u003cli class=\"MsoNormal\"\u003e\u003cspan style=\"mso-ansi-language: EN-GB;\" lang=\"EN-GB\"\u003eA single board can run inference on dozens of cameras as well as support multiple parallel neural networks.\u003c\/span\u003e\u003c\/li\u003e\n\u003cli class=\"MsoNormal\"\u003e\u003cspan style=\"mso-ansi-language: EN-GB;\" lang=\"EN-GB\"\u003eA wide range of end-to-end AI pipelines and models are available out of the box.\u003c\/span\u003e\u003c\/li\u003e\n\u003cli class=\"MsoNormal\"\u003e\u003cspan style=\"mso-ansi-language: EN-GB;\" lang=\"EN-GB\"\u003eHassle free evaluation and SW integration thanks to \u003cstrong\u003eVoyager\u003cmeta charset=\"utf-8\"\u003e® SDK.\u003c\/strong\u003e\u003c\/span\u003e\u003c\/li\u003e\n\u003cli class=\"MsoNormal\"\u003eUncompromised prediction accuracy thanks to advanced quantization tools.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp class=\"p1\"\u003e\u003cstrong\u003eSystem Requirements\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp data-renderer-start-pos=\"1296\"\u003e\u003cmark data-is-hovered=\"false\" data-has-focus=\"false\" data-mark-annotation-state=\"resolved\" class=\"cc-4skef7\" data-id=\"07d941e5-a649-4434-b083-f616d7bcab3b\" data-mark-annotation-type=\"inlineComment\" data-mark-type=\"annotation\" data-renderer-mark=\"true\" aria-disabled=\"true\" id=\"07d941e5-a649-4434-b083-f616d7bcab3b\"\u003e\u003c\/mark\u003eMetis PCIe Card has the following system integration requirements. Our team actively tests integration with different systems from vendors such as Dell, Lenovo, Advantech and Aetina.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli data-renderer-start-pos=\"1502\"\u003eHost Interface: PCIe Gen. 3.0 x4\u003c\/li\u003e\n\u003cli data-renderer-start-pos=\"1538\"\u003eMechanical form factor: PCIe half-height, half-length, single slot (HH, HL, SS)\u003c\/li\u003e\n\u003cli data-renderer-start-pos=\"1621\"\u003ePower Rating: PCI-SIG compliant power slot. \u003cmeta charset=\"utf-8\"\u003e \u003cspan\u003eRefer to Typical Power specs in the \u003ca href=\"https:\/\/support.axelera.ai\/hc\/en-us\/articles\/22698905777810-Metis-PCIe-1-AIPU-Datasheet\"\u003eMetis PCIe 1 AIPU Datasheet \u003c\/a\u003efor typical average power consumed when running inference.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli\u003eHost CPU: Intel® Core™ Processors and Xeon\u003cstrong\u003e®\u003c\/strong\u003e Processors, Ryzen™ Processors, Arm64 (aarch64) based processors.\u003c\/li\u003e\n\u003cli\u003eHost Operating System:\n\u003cul\u003e\n\u003cli data-renderer-start-pos=\"3205\"\u003eNative Linux support is tested on Ubuntu 22.04 and Ubuntu 24.04\u003c\/li\u003e\n\u003cli data-renderer-start-pos=\"3205\"\u003eA  \u003ca style=\"font-family: -apple-system, BlinkMacSystemFont, 'San Francisco', 'Segoe UI', Roboto, 'Helvetica Neue', sans-serif; font-size: 0.875rem;\" data-outlook-id=\"ec026f26-e720-46d7-8bff-828c719f821a\" data-auth=\"NotApplicable\" rel=\"noopener noreferrer\" href=\"https:\/\/eur05.safelinks.protection.outlook.com\/?url=https%3A%2F%2Fsupport.axelera.ai%2Fhc%2Fen-us%2Farticles%2F25953148201362-Install-Voyager-SDK-in-a-Docker-Container\u0026amp;data=05%7C02%7Cwendy.vargas%40axelera.ai%7Cb9c1046c3c9c4d7cef8808dd9246df22%7C9c838ba7c38c416da7931de07a190ebd%7C0%7C0%7C638827555423750785%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C\u0026amp;sdata=VWiCrReAv22sAa54inxg1OU92ErdEQMWO5PincTgvTA%3D\u0026amp;reserved=0\" title=\"Original URL: https:\/\/support.axelera.ai\/hc\/en-us\/articles\/25953148201362-Install-Voyager-SDK-in-a-Docker-Container. Click or tap if you trust this link.\" data-linkindex=\"2\" target=\"_blank\"\u003eDocker Guide\u003c\/a\u003e\u003cspan style=\"font-family: -apple-system, BlinkMacSystemFont, 'San Francisco', 'Segoe UI', Roboto, 'Helvetica Neue', sans-serif; font-size: 0.875rem;\"\u003e is available to evaluate or develop with other Linux distributions.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli data-renderer-start-pos=\"3255\"\u003e\n\u003cspan\u003eNative Windows support for inference is available on Windows 10\/11 and Windows Server 2025. SDK development is only supported on Linux.\u003c\/span\u003e\u003cmeta charset=\"utf-8\"\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003ca rel=\"noopener\" href=\"https:\/\/axelera.ai\/hubfs\/Axelera_February2025\/pdfs\/axelera-ai-pcie-ai-edge-accelerator-card.pdf\" class=\"button\" target=\"_blank\"\u003e\u003cstrong\u003e\u003cspan lang=\"EN-GB\" style=\"mso-ansi-language: EN-GB;\"\u003eDownload the PCIe Product Brief here!\u003c\/span\u003e\u003c\/strong\u003e\u003c\/a\u003e\u003c\/p\u003e\n\u003cstyle\u003e\n.button {\n   background-color: #f4be18;\n   color: #000000;\n   font-size: 16px;\n   padding: 10px 30px;\n   text-align: center;\n   display: inline-block;\n   text-decoration: none; \/* Removes underline *\/\n   border-radius: 22px;\n   transition: background 0.4s ease; \/* Smooth transition *\/\n}\n.button:hover {\n   background: linear-gradient(90deg, #f4be18 50%, #5aa67a 65%, #3e53e5 80%, #3e53e5 90%);\n   color: #fff;\n   text-decoration: none;\n}\n  \n\u003c\/style\u003e\n\u003cp style=\"text-indent: -18.0pt; mso-list: l1 level1 lfo2;\" class=\"MsoListParagraphCxSpFirst\"\u003e\u003c!-- [if !supportLists]--\u003e\u003cspan style=\"font-family: Symbol; mso-fareast-font-family: Symbol; mso-bidi-font-family: Symbol; mso-ansi-language: EN-GB;\" lang=\"EN-GB\"\u003e\u003cspan style=\"mso-list: Ignore;\"\u003e·\u003cspan style=\"font: 7.0pt 'Times New Roman';\"\u003e \u003c\/span\u003e\u003c\/span\u003e\u003c\/span\u003e\u003cspan style=\"mso-ansi-language: EN-GB;\" lang=\"EN-GB\"\u003e\u003c\/span\u003e\u003c\/p\u003e","brand":"Axelera AI","offers":[{"title":"4GB","offer_id":51109413454165,"sku":"AXE-BME20P1AJ04A02","price":379.95,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0879\/1664\/2645\/files\/axelera-metis-ai-accelerator-214tops-pcie-front.jpg?v=1770668170"},{"product_id":"pcie-ai-accelerator-card-powered-by-4-metis-aipu","title":"Metis 4-chip PCIe AI Accelerator Card","description":"\u003cp class=\"MsoNormal\"\u003e\u003cspan lang=\"EN-US\" style=\"mso-ansi-language: EN-US;\"\u003e\u003cstrong\u003eAxelera\u003cmeta charset=\"utf-8\"\u003e® AI’s PCIe card\u003c\/strong\u003e, powered by \u003cstrong\u003e4\u003c\/strong\u003e \u003cstrong\u003eMetis\u003cmeta charset=\"utf-8\"\u003e® AIPU,\u003c\/strong\u003e offers the highest performance inference acceleration on the market, combining ease of use, power efficiency, and scalability.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp class=\"MsoNormal\"\u003e\u003cb\u003e\u003cspan style=\"mso-ansi-language: EN-US;\" lang=\"EN-US\"\u003eKey Benefits:\u003c\/span\u003e\u003c\/b\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli class=\"MsoNormal\"\u003e\u003cspan style=\"mso-ansi-language: EN-GB;\" lang=\"EN-GB\"\u003eThe highest-performance \u003cstrong\u003eAI-accelerator PCIe \u003c\/strong\u003ecard in the market for edge AI applications. Powered by four Metis AIPU.\u003c\/span\u003e\u003c\/li\u003e\n\u003cli class=\"MsoNormal\"\u003e\u003cspan style=\"mso-ansi-language: EN-GB;\" lang=\"EN-GB\"\u003eA single board can run inference on dozens of cameras as well as support multiple parallel neural networks.\u003c\/span\u003e\u003c\/li\u003e\n\u003cli class=\"MsoNormal\"\u003e\u003cspan style=\"mso-ansi-language: EN-GB;\" lang=\"EN-GB\"\u003eA wide range of end-to-end AI pipelines and models are available out of the box.\u003c\/span\u003e\u003c\/li\u003e\n\u003cli class=\"MsoNormal\"\u003e\u003cspan style=\"mso-ansi-language: EN-GB;\" lang=\"EN-GB\"\u003eHassle free evaluation and SW integration thanks to \u003cstrong\u003eVoyager\u003cmeta charset=\"utf-8\"\u003e® SDK.\u003c\/strong\u003e\u003c\/span\u003e\u003c\/li\u003e\n\u003cli class=\"MsoNormal\"\u003eUncompromised prediction accuracy thanks to advanced quantization tools.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003cspan\u003e\u003cstrong\u003eSystem Requirements\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan\u003eMetis 4-AIPU PCIe Card has the following system integration requirements. For full details refer to the \u003c\/span\u003e\u003ca title=\"https:\/\/support.axelera.ai\/hc\/en-us\/articles\/29607357477522-metis-pcie-4-aipu-ai-accelerator-card-datasheet\" class=\"fui-Link ___1q1shib f2hkw1w f3rmtva f1ewtqcl fyind8e f1k6fduh f1w7gpdv fk6fouc fjoy568 figsok6 f1s184ao f1mk8lai fnbmjn9 f1o700av f13mvf36 f1cmlufx f9n3di6 f1ids18y f1tx3yz7 f1deo86v f1eh06m1 f1iescvh fhgqx19 f1olyrje f1p93eir f1nev41a f1h8hb77 f1lqvz6u f10aw75t fsle3fq f17ae5zn\" rel=\"noreferrer noopener\" href=\"https:\/\/support.axelera.ai\/hc\/en-us\/articles\/29607357477522-Metis-PCIe-4-AIPU-AI-Accelerator-Card-Datasheet\" id=\"menur87a\" aria-label=\"Link Datasheet\" target=\"_blank\"\u003eDatasheet\u003c\/a\u003e\u003cspan\u003e. Our team actively tests integration with different systems from vendors such as Dell, Lenovo, Advantech and Aetina.\u003c\/span\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eHost Interface: PCIe Gen. 3.0 x16\u003c\/li\u003e\n\u003cli\u003eMechanical form factor: PCIe full-height, three-quarter length, single slot \u003c\/li\u003e\n\u003cli\u003ePower Rating: 225 W\u003c\/li\u003e\n\u003cli\u003eHost CPU: Intel® Core™ Processors and Xeon\u003cmeta charset=\"utf-8\"\u003e® Processors, Ryzen™ Processors, Arm64 (aarch64) based processors.\u003c\/li\u003e\n\u003cli data-renderer-start-pos=\"3179\"\u003eHost Operating System:\n\u003cul\u003e\n\u003cli data-renderer-start-pos=\"3205\"\u003eNative Linux support is tested on Ubuntu 22.04 and Ubuntu 24.04\u003c\/li\u003e\n\u003cli data-renderer-start-pos=\"3205\"\u003eA \u003ca data-linkindex=\"2\" title=\"Original URL: https:\/\/support.axelera.ai\/hc\/en-us\/articles\/25953148201362-Install-Voyager-SDK-in-a-Docker-Container. Click or tap if you trust this link.\" href=\"https:\/\/eur05.safelinks.protection.outlook.com\/?url=https%3A%2F%2Fsupport.axelera.ai%2Fhc%2Fen-us%2Farticles%2F25953148201362-Install-Voyager-SDK-in-a-Docker-Container\u0026amp;data=05%7C02%7Cwendy.vargas%40axelera.ai%7Cb9c1046c3c9c4d7cef8808dd9246df22%7C9c838ba7c38c416da7931de07a190ebd%7C0%7C0%7C638827555423750785%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C\u0026amp;sdata=VWiCrReAv22sAa54inxg1OU92ErdEQMWO5PincTgvTA%3D\u0026amp;reserved=0\" rel=\"noopener noreferrer\" data-auth=\"NotApplicable\" data-outlook-id=\"ec026f26-e720-46d7-8bff-828c719f821a\" style=\"font-family: -apple-system, BlinkMacSystemFont, 'San Francisco', 'Segoe UI', Roboto, 'Helvetica Neue', sans-serif; font-size: 0.875rem;\" target=\"_blank\"\u003eDocker Guide\u003c\/a\u003e\u003cspan style=\"font-family: -apple-system, BlinkMacSystemFont, 'San Francisco', 'Segoe UI', Roboto, 'Helvetica Neue', sans-serif; font-size: 0.875rem;\"\u003e is available to evaluate or develop with other Linux distributions.\u003c\/span\u003e\n\u003c\/li\u003e\n\u003cli data-renderer-start-pos=\"3255\"\u003e\n\u003cspan\u003eNative Windows support for inference is available on Windows 10\/11 and Windows Server 2025. SDK development is only supported on Linux.\u003c\/span\u003e\u003cmeta charset=\"utf-8\"\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp class=\"MsoNormal\"\u003e\u003cb\u003e\u003cspan lang=\"EN-GB\"\u003eEasy To Integrate\u003c\/span\u003e\u003c\/b\u003e\u003c\/p\u003e\n\u003cp class=\"p1\"\u003eMetis PCIe card integrates seamlessly with host CPUs based on both x86 and ARM architectures. Our team actively tests different systems from vendors such as Dell, Lenovo, Advantech and Aetina.\u003c\/p\u003e\n\u003cp class=\"MsoNormal\"\u003e \u003c\/p\u003e\n\u003cp\u003e\u003ca rel=\"noopener\" href=\"https:\/\/axelera.ai\/hubfs\/Axelera%20AI%20Metis%20PCIe%20x4%20Edge%20Accelerator%20Card.pdf\" class=\"button\" target=\"_blank\"\u003e\u003cstrong\u003e\u003cspan lang=\"EN-GB\" style=\"mso-ansi-language: EN-GB;\"\u003eDownload the PCIe Product Brief here!\u003c\/span\u003e\u003c\/strong\u003e\u003c\/a\u003e\u003c\/p\u003e\n\u003cstyle\u003e\n.button {\n   background-color: #f4be18;\n   color: #000000;\n   font-size: 16px;\n   padding: 10px 30px;\n   text-align: center;\n   display: inline-block;\n   text-decoration: none; \/* Removes underline *\/\n   border-radius: 22px;\n   transition: background 0.4s ease; \/* Smooth transition *\/\n}\n.button:hover {\n   background: linear-gradient(90deg, #f4be18 50%, #5aa67a 65%, #3e53e5 80%, #3e53e5 90%);\n   color: #fff;\n   text-decoration: none;\n}\n\u003c\/style\u003e\n\u003cp style=\"text-indent: -18.0pt; mso-list: l1 level1 lfo2;\" class=\"MsoListParagraphCxSpFirst\"\u003e\u003c!-- [if !supportLists]--\u003e\u003cspan style=\"font-family: Symbol; mso-fareast-font-family: Symbol; mso-bidi-font-family: Symbol; mso-ansi-language: EN-GB;\" lang=\"EN-GB\"\u003e\u003cspan style=\"mso-list: Ignore;\"\u003e·\u003cspan style=\"font: 7.0pt 'Times New Roman';\"\u003e \u003c\/span\u003e\u003c\/span\u003e\u003c\/span\u003e\u003cspan style=\"mso-ansi-language: EN-GB;\" lang=\"EN-GB\"\u003e\u003c\/span\u003e\u003c\/p\u003e","brand":"Axelera AI","offers":[{"title":"16GB - Active Cooling","offer_id":51945747480917,"sku":"AXE-BME20P4AC16A01","price":1770.95,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0879\/1664\/2645\/files\/Axelera-AI-Metis-PCIex4-Fanless-Front.jpg?v=1763566609"}],"url":"https:\/\/store.axelera.ai\/collections\/pcie.oembed","provider":"Axelera AI","version":"1.0","type":"link"}