{"id":120464,"date":"2025-04-28T16:21:30","date_gmt":"2025-04-28T14:21:30","guid":{"rendered":"https:\/\/aixia.se\/nvidia-dgx-b200\/"},"modified":"2026-03-09T14:50:00","modified_gmt":"2026-03-09T13:50:00","slug":"nvidia-dgx-b200","status":"publish","type":"post","link":"https:\/\/aixia.se\/en\/nvidia-dgx-b200\/","title":{"rendered":"NVIDIA DGX B200 &#8211; new hardware for AI training"},"content":{"rendered":"\t\t<div data-elementor-type=\"wp-post\" data-elementor-id=\"120464\" class=\"elementor elementor-120464 elementor-118255\" data-elementor-post-type=\"post\">\n\t\t\t\t<div class=\"elementor-element elementor-element-f9474c4 e-grid e-con-boxed e-con e-parent\" data-id=\"f9474c4\" data-element_type=\"container\" data-e-type=\"container\">\n\t\t\t\t\t<div class=\"e-con-inner\">\n\t\t\t\t<div class=\"elementor-element elementor-element-f14def3 elementor-widget elementor-widget-image\" data-id=\"f14def3\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"image.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img fetchpriority=\"high\" decoding=\"async\" width=\"800\" height=\"988\" src=\"https:\/\/aixia.se\/wp-content\/uploads\/2025\/04\/DGXB200-829x1024.png\" class=\"attachment-large size-large wp-image-118259\" alt=\"\" srcset=\"https:\/\/aixia.se\/wp-content\/uploads\/2025\/04\/DGXB200-829x1024.png 829w, https:\/\/aixia.se\/wp-content\/uploads\/2025\/04\/DGXB200-243x300.png 243w, https:\/\/aixia.se\/wp-content\/uploads\/2025\/04\/DGXB200-768x949.png 768w, https:\/\/aixia.se\/wp-content\/uploads\/2025\/04\/DGXB200.png 844w\" sizes=\"(max-width: 800px) 100vw, 800px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<div class=\"elementor-element elementor-element-47fd6c9 elementor-widget elementor-widget-text-editor\" data-id=\"47fd6c9\" data-element_type=\"widget\" data-e-type=\"widget\" data-widget_type=\"text-editor.default\">\n\t\t\t\t<div class=\"elementor-widget-container\">\n\t\t\t\t\t\t\t\t\t<h2 class=\"\" data-start=\"128\" data-end=\"212\">NVIDIA DGX B200 &#8211; now available for POC and evaluation<\/h2><p class=\"\" data-start=\"214\" data-end=\"333\"><span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Aixia is proud to announce that we now have the latest generation AI infrastructure, <strong data-start=\"91\" data-end=\"110\">NVIDIA DGX B200<\/strong>, fully operational in our data center.<\/span> <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">With this investment, we strengthen our position as a leader in advanced AI and HPC solutions in the Nordic region.<\/span><\/p><h3 class=\"\" data-start=\"335\" data-end=\"365\">A new level of AI performance<\/h3><p class=\"\" data-start=\"367\" data-end=\"486\"><span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Based on NVIDIA&#8217;s new Blackwell architecture, DGX B200 delivers up to <strong data-start=\"79\" data-end=\"107\">72 petaFLOPS for training<\/strong> and <strong data-start=\"112\" data-end=\"142\">144 petaFLOPS for inference<\/strong>.<\/span> <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">The system is equipped with eight NVIDIA Blackwell GPUs and a total of <strong data-start=\"65\" data-end=\"93\">1,440 GB of HBM3e GPU memory<\/strong>, enabling it to handle the most demanding AI workloads, including large language models and generative AI.<\/span><\/p><h3 class=\"\" data-start=\"488\" data-end=\"524\">Technical specification in brief:<\/h3><ul data-start=\"526\" data-end=\"1020\"><li class=\"\" data-start=\"526\" data-end=\"574\"><p class=\"\" data-start=\"528\" data-end=\"574\"><strong data-start=\"528\" data-end=\"535\">GPU<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">8x NVIDIA Blackwell<\/span><\/p><\/li><li class=\"\" data-start=\"575\" data-end=\"631\"><p class=\"\" data-start=\"577\" data-end=\"631\"><strong data-start=\"577\" data-end=\"590\">GPU memory<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">1 440 GB HBM3e<\/span><\/p><\/li><li class=\"\" data-start=\"632\" data-end=\"682\"><p class=\"\" data-start=\"634\" data-end=\"682\"><strong data-start=\"634\" data-end=\"641\">CPU<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">2x Intel Xeon Platinum 8570 (112 cores in total)<\/span><\/p><\/li><li class=\"\" data-start=\"683\" data-end=\"741\"><p class=\"\" data-start=\"685\" data-end=\"741\"><strong data-start=\"685\" data-end=\"700\">System memory<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Up to 4 TB<\/span><\/p><\/li><li class=\"\" data-start=\"742\" data-end=\"796\"><p class=\"\" data-start=\"744\" data-end=\"796\"><strong data-start=\"744\" data-end=\"755\">Storage<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">2x 1.9 TB NVMe M.2 (OS) + 8x 3.84 TB NVMe U.2 (data)<\/span><\/p><\/li><li class=\"\" data-start=\"797\" data-end=\"851\"><p class=\"\" data-start=\"799\" data-end=\"851\"><strong data-start=\"799\" data-end=\"810\">Network<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">8x NVIDIA ConnectX-7 VPI (up to 400 Gb\/s)<\/span><\/p><\/li><li class=\"\" data-start=\"852\" data-end=\"916\"><p class=\"\" data-start=\"854\" data-end=\"916\"><strong data-start=\"854\" data-end=\"875\">Power consumption<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">~14.3 kW<\/span><\/p><\/li><li class=\"\" data-start=\"917\" data-end=\"1020\"><p class=\"\" data-start=\"919\" data-end=\"1020\"><strong data-start=\"919\" data-end=\"933\">Form factor<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">10U<\/span><\/p><\/li><\/ul><p class=\"\" data-start=\"1022\" data-end=\"1107\"><span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">The system comes with <strong data-start=\"23\" data-end=\"47\">NVIDIA AI Enterprise<\/strong> and <strong data-start=\"52\" data-end=\"75\">NVIDIA Base Command<\/strong>, providing a complete software stack for AI development and operation.<\/span><\/p><h3 data-start=\"1109\" data-end=\"1162\"> <\/h3><h3 class=\"\" data-start=\"1109\" data-end=\"1162\">Proof of Concept &#8211; in our data center or at yours<\/h3><p class=\"\" data-start=\"1164\" data-end=\"1249\"><span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">We now offer companies the opportunity to carry out <strong data-start=\"49\" data-end=\"75\">proof of concept (POC<\/strong>) projects with the DGX B200.<\/span><\/p><ul data-start=\"1251\" data-end=\"1424\"><li class=\"\" data-start=\"1251\" data-end=\"1315\"><p class=\"\" data-start=\"1253\" data-end=\"1315\"><strong data-start=\"1253\" data-end=\"1274\">In our data center<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Test and develop your AI models in an optimized environment with access to our expertise.<\/span><\/p><\/li><li class=\"\" data-start=\"1316\" data-end=\"1424\"><p class=\"\" data-start=\"1318\" data-end=\"1424\"><strong data-start=\"1318\" data-end=\"1337\">On site<\/strong>: <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Evaluate the DGX B200 in your own infrastructure to see how it integrates into your workflows.<\/span><\/p><\/li><\/ul><p class=\"\" data-start=\"1426\" data-end=\"1511\"><span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Whatever your choice, we will support you throughout the process, from planning to implementation.<\/span><\/p><p class=\"\" data-start=\"1426\" data-end=\"1511\">\u200b<\/p><h3 class=\"\" data-start=\"1513\" data-end=\"1549\"><a href=\"https:\/\/aixia.se\/en\/contact-us\/\">Contact us for more information<\/a><\/h3><p class=\"\" data-start=\"1551\" data-end=\"1676\"><span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Interested in exploring how NVIDIA DGX B200 can accelerate your AI initiatives?<\/span> <span class=\"relative -mx-px my-[-0.2rem] rounded px-px py-[0.2rem] transition-colors duration-100 ease-in-out\">Contact us at Aixia to discuss your needs and how we can help you realize them.<\/span><\/p>\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"<p>NVIDIA DGX B200 &#8211; now available for POC and evaluation Aixia is proud to announce that we now have the latest generation AI infrastructure, NVIDIA DGX B200, fully operational in [&hellip;]<\/p>\n","protected":false},"author":4,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"inline_featured_image":false,"footnotes":""},"categories":[46],"tags":[],"class_list":["post-120464","post","type-post","status-publish","format-standard","hentry","category-news"],"acf":[],"aioseo_notices":[],"_links":{"self":[{"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/posts\/120464","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/comments?post=120464"}],"version-history":[{"count":2,"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/posts\/120464\/revisions"}],"predecessor-version":[{"id":121250,"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/posts\/120464\/revisions\/121250"}],"wp:attachment":[{"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/media?parent=120464"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/categories?post=120464"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/aixia.se\/en\/wp-json\/wp\/v2\/tags?post=120464"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}