{"product_id":"nvidia-dgx-spark-founders-edition-ai-supercomputer","title":"NVIDIA DGX Spark Founders Edition  AI Supercomputer","description":"\n    \u003cdiv style=\"font-family: 'Helvetica Neue', Arial, sans-serif; max-width: 800px; margin: 0 auto; padding: 20px;\"\u003e\n        \u003cdiv style=\"margin-top: 20px;\"\u003e\n            \u003cdiv class=\"kw-advanced-pbtech\" style=\"font-family:'Helvetica Neue',Arial,sans-serif;color:#333;line-height:1.7;max-width:860px;margin:0 auto;\"\u003e\n\u003ch2\u003eFeatures\u003c\/h2\u003e\n\u003cdiv data-block=\"features\" data-scroll-amount=\"100\" data-scroll-top=\"true\" data-trigger-css=\"d-xl-none\"\u003e\n\u003cdiv\u003e\n\u003cdiv\u003e\n\u003cdiv\u003e\n\u003ch3\u003eNVIDIA DGX Spark\u003c\/h3\u003e\n\u003cp\u003eThe power of NVIDIA Grace Blackwell on your desk.\u003c\/p\u003e\n\u003cp\u003e\u003cnoscript\u003e\u003c\/noscript\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003ch3\u003eSpark Something Big\u003c\/h3\u003e\n\u003cp\u003ePowered by the NVIDIA GB10 Grace Blackwell Superchip, NVIDIA DGX Spark™ delivers up to one petaFLOP1 of FP4 AI performance in a power-efficient, compact form factor. With a preinstalled NVIDIA AI software stack and 128 GB of memory, developers can prototype, fine-tune, and deploy the latest reasoning AI models. Additionally, NVIDIA NemoClaw, part of the NVIDIA Agent Toolkit is an open source agent development platform for building, evaluating, and optimizing safer, long-running autonomous agents directly from the desktop.\u003c\/p\u003e\n\u003cp\u003e[1] Theoretical FP4 TOPS using the sparsity feature. \u003c\/p\u003e\n\u003ch3\u003eRun Autonomous Agents More Safely\u003c\/h3\u003e\n\u003cp\u003eNVIDIA NemoClaw is an open source stack that adds privacy and security controls to OpenClaw. With one command, anyone can run always-on, self-evolving agents anywhere.\u003c\/p\u003e\n\u003cp\u003e\u003cnoscript\u003e\u003c\/noscript\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003ch3\u003eNVIDIA GPU, CPU, Networking, and AI Software Technologies\u003c\/h3\u003e\n\u003cp\u003e\u003cstrong\u003eNVIDIA GB10 Superchip\u003cbr\u003e\u003c\/strong\u003eExperience up to  1 petaFLOP  of AI performance at FP4 precision with the NVIDIA Grace Blackwell architecture.\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003e128 GB of Coherent Unified System Memory\u003cbr\u003e\u003c\/strong\u003eRun AI development and testing workloads with AI models up to 200 billion parameters at your desktop with a large, unified system memory.\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eNVIDIA ConnectX Networking\u003cbr\u003e\u003c\/strong\u003eHigh-performance NVIDIA ConnectX™ networking enables the connection of two NVIDIA DGX Spark systems to work with AI models of up to 405 billion parameters.\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eNVIDIA AI Software Stack\u003cbr\u003e\u003c\/strong\u003eUtilize a full-stack solution for generative AI workloads, encompassing NVIDIA tools, frameworks, libraries, and pre-trained models including NVIDIA NIM.\u003c\/p\u003e\n\u003ch3\u003eAccelerate All AI Workloads\u003c\/h3\u003e\n\u003cp\u003eDelivering the power of Grace Blackwell  in a desktop-friendly size, NVIDIA DGX Spark is ideal for AI developer, researcher, and data scientist workloads.\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003ePrototyping\u003cbr\u003e\u003c\/strong\u003eDevelop, test, and validate AI models and applications.\u003c\/p\u003e\n\u003cp\u003e\u003cnoscript\u003e\u003c\/noscript\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eFine-Tuning\u003cbr\u003e\u003c\/strong\u003eFine-tune AI models up to 70 billion parameters.\u003c\/p\u003e\n\u003cp\u003e\u003cnoscript\u003e\u003c\/noscript\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eInference\u003cbr\u003e\u003c\/strong\u003eTest, validate, and inference with AI models up to 200 billion parameters.\u003c\/p\u003e\n\u003cp\u003e\u003cnoscript\u003e\u003c\/noscript\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eData Science\u003cbr\u003e\u003c\/strong\u003eHigh-performance data science at your desk.\u003c\/p\u003e\n\u003cp\u003e\u003cnoscript\u003e\u003c\/noscript\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eEdge Applications\u003cbr\u003e\u003c\/strong\u003eDevelop edge applications with NVIDIA AI frameworks, including NVIDIA Isaac™, Metropolis, and many others.\u003c\/p\u003e\n\u003cp\u003e\u003cnoscript\u003e\u003c\/noscript\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003ch3\u003eNVIDIA AI Enterprise-DGX Spark\u003c\/h3\u003e\n\u003cp\u003eA cloud-native suite of software tools, libraries, and frameworks accelerating production-grade AI development. Combines enterprise-grade security, optimized performance, and enterprise-level support to streamline prototype-to-production for next-gen agentic AI.\u003c\/p\u003e\n\u003cp\u003e\u003cnoscript\u003e\u003c\/noscript\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003ch3\u003eDGX Spark AI Software\u003c\/h3\u003e\n\u003cp\u003eDGX Spark includes the NVIDIA AI software stack preinstalled with support for the NVIDIA AI software ecosystem to get AI projects up and running quickly.\u003c\/p\u003e\n\u003cp\u003e\u003cnoscript\u003e\u003c\/noscript\u003e\u003c\/p\u003e \u003c\/div\u003e\n\u003cbr\u003e \u003cdiv data-block-id=\"11826\"\u003e\n\u003cdiv\u003e\u003cdiv\u003e\n\u003cdiv\u003e\n\u003cdiv\u003e\n\u003cp\u003e\u003ca href=\"system-builder\"\u003e \u003cpicture\u003e \u003csource media=\"(min-width: 768px)\" srcset=\"https:\/\/www.pbtech.co.nz\/fileslib\/20220825175232_custom-build-your-pc-0822-desktop-001.webp\" type=\"image\/webp\"\u003e \u003csource media=\"(min-width: 0px)\" srcset=\"https:\/\/www.pbtech.co.nz\/fileslib\/20220825175234_custom-build-your-pc-0822-mobile-001.webp\" type=\"image\/webp\"\u003e \u003csource media=\"(min-width: 768px)\" srcset=\"https:\/\/www.pbtech.co.nz\/fileslib\/20220825175232_custom-build-your-pc-0822-desktop-001.jpg\" type=\"image\/jpeg\"\u003e \u003csource media=\"(min-width: 0px)\" srcset=\"https:\/\/www.pbtech.co.nz\/fileslib\/20220825175234_custom-build-your-pc-0822-mobile-001.jpg\" type=\"image\/jpeg\"\u003e\u003c\/source\u003e\u003c\/source\u003e\u003c\/picture\u003e \u003c\/a\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"font-size: 16px;\"\u003e\u003cstrong\u003eFrequently asked questions\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eCan I swap out parts and\/or add\/change\/remove operating systems in a KW Tech PC?\u003c\/strong\u003e\u003cbr\u003e\u003cbr\u003eWe can add any part to a PC for a small fee as long as we don't need to remove an existing part for it to fit, for example adding more RAM, an extra hard drive, installing a Windows OS, or adding a graphics card to a PC without one (we can even SLI\/Crossfire for you if it is compatible). We cannot change components that are part of an existing build e.g. Upgrade an existing graphics card or add a SSD with Windows installed if the PC only has a single hard drive (as the OS is already pre-installed). If you do have a specific requirement, then one of our experienced sales team will be happy to build a system that suits your needs.\u003c\/p\u003e\n\u003cp\u003e\u003ca href=\"contact\" target=\"_self\"\u003eContact our WebSales team here\u003c\/a\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eWhat parts are used in this PC?\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp\u003eThe parts are subject to change depending on stock availability but the specifications listed in the title will always be correct. If you have specific parts you are after, one of our experienced sales team will be happy to build a system that suits your needs. \u003c\/p\u003e\n\u003cp\u003eOnce again, you can \u003ca href=\"contact\" target=\"_self\"\u003econtact our WebSales team here\u003c\/a\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eI've just purchased my first custom PC, how do I set it up?\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp\u003eOur short new PC setup guide shows you how to safely unbox it, and set it all up so you can get to work or start playing games.\u003c\/p\u003e\n\u003cp\u003eYour can \u003ca href=\"pb-tech-pc-setup-guide\" title=\"See more in the PB Tech new PC setup guide\"\u003elearn more in our new PC setup guide here\u003c\/a\u003e\u003c\/p\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cdiv\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cdiv\u003e\u003c\/div\u003e\n\u003ch2\u003eSpecifications\u003c\/h2\u003e\n\u003cdiv data-block=\"specifications\" data-scroll-amount=\"100\" data-scroll-top=\"true\" data-trigger-css=\"d-xl-none\"\u003e\n\u003cdiv\u003e\n\u003ch3 style=\"font-size:16px;font-weight:700;margin-top:24px;\"\u003eTechnical Specifications\u003c\/h3\u003e\n\u003ctable style=\"border-collapse:collapse;width:100%;font-size:14px;margin-top:8px;\"\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eArchitecture\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003eNVIDIA Grace Blackwell\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eGPU\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003eBlackwell Architecture\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eCPU\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003e20-core Arm, 10 Cortex-X925 + 10 Cortex-A725 Arm\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eCUDA Cores\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003eBlackwell Generation\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eTensor Cores\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003e5th Generation\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eRT Cores\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003e4th Generation\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eTensor Performance[1]\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003eUp to 1 PFLOP FP4\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eSystem Memory\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003e128 GB LPDDR5x, coherent unified system memory\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eMemory Interface\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003e256-bit\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eMemory Bandwidth\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003e273 GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eStorage\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003e4 TB NVME.M2 with self-encryption\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eUSB\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003e4x USB TypeC\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eEthernet\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003e1x RJ-45 connector10 GbE\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eNIC\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003eConnectX-7 NIC @ 200 Gbps\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eWi-Fi\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003eWiFi 7\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eBluetooth\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003eBT 5.4\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eAudio-output\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003eHDMI multichannel audio output\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003ePower Supply\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003e240 W\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eGB10 TDP[2]\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003e140 W\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eDisplay Connectors\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003e1x HDMI 2.1a\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eNVENC | NVDEC\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003e1x | 1x\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eOS\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003eNVIDIA DGX™ OS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eSystem Dimensions\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003e150 mm L x 150 mm W x 50.5 mm H\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eSystem Weight\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003e1.2 kg\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth style=\"border:1px solid #ddd;padding:9px 14px;background:#f8f8f8;width:35%;font-weight:600;text-align:left;\"\u003eNote\u003c\/th\u003e\n\u003ctd style=\"border:1px solid #ddd;padding:9px 14px;\"\u003e[1] Theoretical FP4 TOPS using the sparsity feature.[2] TDP: Thermal Design Power of the GB10 chip including CPU and GPU\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/table\u003e\n\u003c\/div\u003e\n\u003cdiv\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cdiv\u003e\u003c\/div\u003e\n\u003c\/div\u003e\n        \u003c\/div\u003e\n    \u003c\/div\u003e\n    ","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":67011489628205,"sku":"940-54242-0002-000","price":11763.24,"currency_code":"NZD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0759\/5088\/2861\/files\/WKSNV0001__1.jpg?v=1783695250","url":"https:\/\/kwtech.co.nz\/products\/nvidia-dgx-spark-founders-edition-ai-supercomputer","provider":"KW Tech","version":"1.0","type":"link"}