{"product_id":"msi-edgexpert-42smy-personal-ai-supercomputer","title":"MSI EdgeXpert 42SMY Personal AI Supercomputer","description":"\u003ch2\u003e\u003cstrong\u003eProduct Features:\u003c\/strong\u003e\u003c\/h2\u003e\n\u003cdiv\u003e\u003c!-- x-tinymce\/html --\u003e\u003c\/div\u003e\n\u003cul\u003e\n\u003cli\u003eGB10 Grace Blackwell Superchip (1petaFLOP AI performance Blackwell GPU, 20-core Arm CPU)\n\u003cul\u003e\n\u003cli\u003eAccelerates AI, Data Science, compute, rendering, and visualization\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/li\u003e\n\u003cli\u003eWorkloads 128GB coherent unified system memory\n\u003cul\u003e\n\u003cli\u003eWork with large AI models of up to 200 billion parameters, fine-tune\u003cbr\u003emodels of up to 70 billion parameters\u003c\/li\u003e\n\u003cli\u003e~100GB of system memory available for user workloads\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/li\u003e\n\u003cli\u003eConnectX-7 networking\n\u003cul\u003e\n\u003cli\u003eConnect two EdgeXpert systems together to work with models of\u003cbr\u003eup to 405 billion parameters\u003c\/li\u003e\n\u003cli\u003eA maximum of 2 DGX Spark systems can be clustered together\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/li\u003e\n\u003cli\u003eDGX OS \u0026amp; NVIDIA AI software stack\n\u003cul\u003e\n\u003cli\u003eSeamlessly move workloads from EdgeXpert to DGX Cloud or any\u003cbr\u003eaccelerated data center or cloud infrastructure\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/li\u003e\n\u003cli\u003eFlexible deployment configurations\n\u003cul\u003e\n\u003cli\u003eConfigure as an AI Workstation or network connected personal AI\u003cbr\u003ecloud\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/li\u003e\n\u003cli\u003eCompact, power efficient design\n\u003cul\u003e\n\u003cli\u003eEasily fits on any desk, powered by standard wall outlet\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003cp\u003e\u003c!-- more --\u003e\u003c\/p\u003e\n\u003ch2\u003e\u003cstrong\u003eSpecification:\u003c\/strong\u003e\u003c\/h2\u003e\n\u003ctable border=\"1\" cellpadding=\"1\" cellspacing=\"1\" style=\"width: 600px; height: 619.813px;\"\u003e\n\u003ctbody\u003e\n\u003ctr style=\"height: 19.5938px;\"\u003e\n\u003ctd style=\"height: 19.5938px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eARCHITECTURE\u003c\/td\u003e\n\u003ctd style=\"height: 19.5938px; width: 356.047px;\"\u003eNVIDIA® Grace Blackwell\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5938px;\"\u003e\n\u003ctd style=\"height: 19.5938px; width: 130.953px;\"\u003eGPU\u003c\/td\u003e\n\u003ctd style=\"height: 19.5938px; width: 356.047px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eNVIDIA® Blackwell Architecture\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5938px;\"\u003e\n\u003ctd style=\"height: 19.5938px; width: 130.953px;\"\u003eCPU\u003c\/td\u003e\n\u003ctd style=\"height: 19.5938px; width: 356.047px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eArm 20 core, 10 Cortex-X925 + 10 Cortex-A725\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5938px;\"\u003e\n\u003ctd style=\"height: 19.5938px; width: 130.953px;\"\u003eCUDA CORES\u003c\/td\u003e\n\u003ctd style=\"height: 19.5938px; width: 356.047px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eBlackwell Generation\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5938px;\"\u003e\n\u003ctd style=\"height: 19.5938px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eTENSOR CORES\u003c\/td\u003e\n\u003ctd style=\"height: 19.5938px; width: 356.047px;\"\u003e5th Generation\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 39.1875px;\"\u003e\n\u003ctd style=\"height: 39.1875px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eTENSOR CORE SUPPORTED DATA FORMATS\u003c\/td\u003e\n\u003ctd style=\"height: 39.1875px; width: 356.047px;\"\u003eTF32, FP16, BF16, INT8, FP8, FP6, FP4\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 39.1875px;\"\u003e\n\u003ctd style=\"height: 39.1875px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eRT CORES\u003c\/td\u003e\n\u003ctd style=\"height: 39.1875px; width: 356.047px;\"\u003e4th Generation\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 39.1875px;\"\u003e\n\u003ctd style=\"height: 39.1875px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eTENSOR PERFORMANCE\u003c\/td\u003e\n\u003ctd style=\"height: 39.1875px; width: 356.047px;\"\u003e1 petaFLOP AI performance (FP4, Sparse)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 39.1875px;\"\u003e\n\u003ctd style=\"height: 39.1875px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eSYSTEM MEMORY\u003c\/td\u003e\n\u003ctd style=\"height: 39.1875px; width: 356.047px;\"\u003e128 GB LPDDR5x, unified system memory\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 55.1875px;\"\u003e\n\u003ctd style=\"height: 55.1875px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eMEMORY INTERFACE\u003c\/td\u003e\n\u003ctd style=\"height: 55.1875px; width: 356.047px;\"\u003e256-bit\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5938px;\"\u003e\n\u003ctd style=\"height: 19.5938px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eMEMORY BANDWITH\u003c\/td\u003e\n\u003ctd style=\"height: 19.5938px; width: 356.047px;\"\u003e273 GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5938px;\"\u003e\n\u003ctd style=\"height: 19.5938px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eSTORAGE\u003c\/td\u003e\n\u003ctd style=\"height: 19.5938px; width: 356.047px;\"\u003e4 TB NVME.M2 with self-encryption\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5938px;\"\u003e\n\u003ctd style=\"height: 19.5938px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eUSB\u003c\/td\u003e\n\u003ctd style=\"height: 19.5938px; width: 356.047px;\"\u003e4x USB 3.2 Type C (up to 20Gb\/s)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 58.7812px;\"\u003e\n\u003ctd style=\"height: 58.7812px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eETHERNET\u003c\/td\u003e\n\u003ctd style=\"height: 58.7812px; width: 356.047px;\"\u003e1x RJ-45 connector 10 GbE\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5938px;\"\u003e\n\u003ctd style=\"height: 19.5938px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eNIC\u003c\/td\u003e\n\u003ctd style=\"height: 19.5938px; width: 356.047px;\"\u003eConnectX-7 Smart NIC\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 39.1875px;\"\u003e\n\u003ctd style=\"height: 39.1875px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eWi-Fi\u003c\/td\u003e\n\u003ctd style=\"height: 39.1875px; width: 356.047px;\"\u003eWiFi 7\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5938px;\"\u003e\n\u003ctd style=\"height: 19.5938px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eBLUETOOTH\u003c\/td\u003e\n\u003ctd style=\"height: 19.5938px; width: 356.047px;\"\u003eBT 5.4\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5938px;\"\u003e\n\u003ctd style=\"height: 19.5938px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eAUDIO OUTPUT\u003c\/td\u003e\n\u003ctd style=\"height: 19.5938px; width: 356.047px;\"\u003eHDMI multichannel audio output\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5938px;\"\u003e\n\u003ctd style=\"height: 19.5938px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eSYSTEM WEIGHT\u003c\/td\u003e\n\u003ctd style=\"height: 19.5938px; width: 356.047px;\"\u003e1.2 kg\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5938px;\"\u003e\n\u003ctd style=\"height: 19.5938px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eDISPLAY CONNECTOR\u003c\/td\u003e\n\u003ctd style=\"height: 19.5938px; width: 356.047px;\"\u003e1 x HDMI 2.1, 4x DP1.4a via USB-C\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5938px;\"\u003e\n\u003ctd style=\"height: 19.5938px; width: 130.953px;\"\u003eNVENC | NVDEC\u003c\/td\u003e\n\u003ctd style=\"height: 19.5938px; width: 356.047px;\"\u003e1x | 1x\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 39.1875px;\"\u003e\n\u003ctd style=\"height: 39.1875px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eOS\u003c\/td\u003e\n\u003ctd style=\"height: 39.1875px; width: 356.047px;\"\u003eNVIDIA® DGX™ OS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 39.1875px;\"\u003e\n\u003ctd style=\"height: 39.1875px; width: 130.953px;\"\u003e\n\u003c!-- x-tinymce\/html --\u003eSYSTEM DIMENSIONS\u003c\/td\u003e\n\u003ctd style=\"height: 39.1875px; width: 356.047px;\"\u003e151 mm L x 151 mm W x 52 mm H (1.2L)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e","brand":"MSI Store | Malaysia","offers":[{"title":"Default Title","offer_id":52693419622720,"sku":"DC-MSI-EDGEXPERT-42SMY-BGB104TG5","price":21999.0,"currency_code":"MYR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0761\/7970\/2080\/files\/Web_EdgeXpert_1.jpg?v=1782354007","url":"https:\/\/my-store.msi.com\/products\/msi-edgexpert-42smy-personal-ai-supercomputer","provider":"MSI Store | Malaysia","version":"1.0","type":"link"}