{"title":"AI Computers \u0026 Workstations","description":"\u003cp\u003eExplore compact systems for local AI development, inference and model experimentation. Check each model’s operating system, processor architecture and software requirements before ordering.\u003c\/p\u003e\u003cp\u003eOur MSI EdgeXpert runs NVIDIA DGX OS on Arm. Contact CCTV Guru for help selecting a compatible system or planning a multi-system installation.\u003c\/p\u003e","products":[{"product_id":"msi-edgexpert-34sau-ai-workstation-gb10-128gb-4tb","title":"MSI EdgeXpert AI Workstation | NVIDIA GB10, 128GB, 4TB","description":"\u003cdiv class=\"cg-premium-wrap\"\u003e\n\u003cp class=\"cg-eyebrow\"\u003e\u003cstrong\u003eMSI · NVIDIA GB10 · LOCAL AI WORKSTATION\u003c\/strong\u003e\u003c\/p\u003e\n\u003ch2 class=\"cg-section-h2\"\u003eA compact AI development platform for your desk\u003c\/h2\u003e\n\u003cp\u003eBuild and test compatible AI applications locally with the MSI EdgeXpert-34SAU. The NVIDIA GB10 Grace Blackwell Superchip, 128GB unified memory and 4TB Gen5 NVMe SSD bring substantial model capacity into a compact desktop system, backed by a 3-year Australian on-site warranty.\u003c\/p\u003e\n\n\u003ch2 class=\"cg-section-h2\"\u003eThe configuration you are buying\u003c\/h2\u003e\n\u003cp\u003e\u003cstrong\u003eEdgeXpert-34SAU · 128GB LPDDR5x · 4TB Gen5 NVMe · NVIDIA DGX OS.\u003c\/strong\u003e This page describes the Australian configuration. Other regional bundles, memory options and promotional illustrations may differ. The price is for one system.\u003c\/p\u003e\n\u003ch2 class=\"cg-section-h2\"\u003eWhat the hardware does for your work\u003c\/h2\u003e\n\u003cdiv class=\"cg-feature-grid\"\u003e\n\u003cdiv class=\"cg-feature-item\"\u003e\n\u003ch3 class=\"cg-feature-item-title cg-section-h2\"\u003e\n\u003cspan class=\"cg-feature-icon\"\u003e\u003csvg class=\"cg-icon\" width=\"26\" height=\"26\" viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.7\" aria-hidden=\"true\"\u003e\u003crect x=\"4\" y=\"4\" width=\"16\" height=\"16\" rx=\"3\"\u003e\u003c\/rect\u003e\u003cpath d=\"m8 12 3 3 5-6\"\u003e\u003c\/path\u003e\u003c\/svg\u003e\u003c\/span\u003e\u003cspan class=\"cg-feature-pill__text\"\u003eGB10 Grace Blackwell\u003c\/span\u003e\n\u003c\/h3\u003e\n\u003cp\u003eA 20-core Arm CPU and NVIDIA Blackwell GPU work together in a platform designed for AI development and inference.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-feature-item\"\u003e\n\u003ch3 class=\"cg-feature-item-title cg-section-h2\"\u003e\n\u003cspan class=\"cg-feature-icon\"\u003e\u003csvg class=\"cg-icon\" width=\"26\" height=\"26\" viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.7\" aria-hidden=\"true\"\u003e\u003crect x=\"4\" y=\"4\" width=\"16\" height=\"16\" rx=\"3\"\u003e\u003c\/rect\u003e\u003cpath d=\"m8 12 3 3 5-6\"\u003e\u003c\/path\u003e\u003c\/svg\u003e\u003c\/span\u003e\u003cspan class=\"cg-feature-pill__text\"\u003e128GB unified memory\u003c\/span\u003e\n\u003c\/h3\u003e\n\u003cp\u003eA coherent memory pool is shared by the CPU and GPU, giving compatible large-model workloads room to operate.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-feature-item\"\u003e\n\u003ch3 class=\"cg-feature-item-title cg-section-h2\"\u003e\n\u003cspan class=\"cg-feature-icon\"\u003e\u003csvg class=\"cg-icon\" width=\"26\" height=\"26\" viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.7\" aria-hidden=\"true\"\u003e\u003crect x=\"4\" y=\"4\" width=\"16\" height=\"16\" rx=\"3\"\u003e\u003c\/rect\u003e\u003cpath d=\"m8 12 3 3 5-6\"\u003e\u003c\/path\u003e\u003c\/svg\u003e\u003c\/span\u003e\u003cspan class=\"cg-feature-pill__text\"\u003e4TB Gen5 NVMe storage\u003c\/span\u003e\n\u003c\/h3\u003e\n\u003cp\u003eStore model files, datasets, containers and development environments locally. Available space is lower after formatting and software installation.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-feature-item\"\u003e\n\u003ch3 class=\"cg-feature-item-title cg-section-h2\"\u003e\n\u003cspan class=\"cg-feature-icon\"\u003e\u003csvg class=\"cg-icon\" width=\"26\" height=\"26\" viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.7\" aria-hidden=\"true\"\u003e\u003crect x=\"4\" y=\"4\" width=\"16\" height=\"16\" rx=\"3\"\u003e\u003c\/rect\u003e\u003cpath d=\"m8 12 3 3 5-6\"\u003e\u003c\/path\u003e\u003c\/svg\u003e\u003c\/span\u003e\u003cspan class=\"cg-feature-pill__text\"\u003eNVIDIA DGX OS\u003c\/span\u003e\n\u003c\/h3\u003e\n\u003cp\u003eAn Ubuntu Linux-based environment for the NVIDIA AI software ecosystem. Check Linux\/Arm support for your chosen tools.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-feature-item\"\u003e\n\u003ch3 class=\"cg-feature-item-title cg-section-h2\"\u003e\n\u003cspan class=\"cg-feature-icon\"\u003e\u003csvg class=\"cg-icon\" width=\"26\" height=\"26\" viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.7\" aria-hidden=\"true\"\u003e\u003crect x=\"4\" y=\"4\" width=\"16\" height=\"16\" rx=\"3\"\u003e\u003c\/rect\u003e\u003cpath d=\"m8 12 3 3 5-6\"\u003e\u003c\/path\u003e\u003c\/svg\u003e\u003c\/span\u003e\u003cspan class=\"cg-feature-pill__text\"\u003e10GbE networking\u003c\/span\u003e\n\u003c\/h3\u003e\n\u003cp\u003eThe RJ45 Ethernet interface supports fast links to a compatible network. End-to-end speed depends on the switch, cable and other devices.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-feature-item\"\u003e\n\u003ch3 class=\"cg-feature-item-title cg-section-h2\"\u003e\n\u003cspan class=\"cg-feature-icon\"\u003e\u003csvg class=\"cg-icon\" width=\"26\" height=\"26\" viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.7\" aria-hidden=\"true\"\u003e\u003crect x=\"4\" y=\"4\" width=\"16\" height=\"16\" rx=\"3\"\u003e\u003c\/rect\u003e\u003cpath d=\"m8 12 3 3 5-6\"\u003e\u003c\/path\u003e\u003c\/svg\u003e\u003c\/span\u003e\u003cspan class=\"cg-feature-pill__text\"\u003eConnectX-7 expansion\u003c\/span\u003e\n\u003c\/h3\u003e\n\u003cp\u003eHigh-speed networking supports planned multi-system AI deployments. Interconnect equipment and configuration are separate.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-feature-item\"\u003e\n\u003ch3 class=\"cg-feature-item-title cg-section-h2\"\u003e\n\u003cspan class=\"cg-feature-icon\"\u003e\u003csvg class=\"cg-icon\" width=\"26\" height=\"26\" viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.7\" aria-hidden=\"true\"\u003e\u003crect x=\"4\" y=\"4\" width=\"16\" height=\"16\" rx=\"3\"\u003e\u003c\/rect\u003e\u003cpath d=\"m8 12 3 3 5-6\"\u003e\u003c\/path\u003e\u003c\/svg\u003e\u003c\/span\u003e\u003cspan class=\"cg-feature-pill__text\"\u003eCompact desktop design\u003c\/span\u003e\n\u003c\/h3\u003e\n\u003cp\u003eThe 151 × 151 × 52 mm chassis fits a development workspace while retaining dedicated cooling.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-feature-item\"\u003e\n\u003ch3 class=\"cg-feature-item-title cg-section-h2\"\u003e\n\u003cspan class=\"cg-feature-icon\"\u003e\u003csvg class=\"cg-icon\" width=\"26\" height=\"26\" viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"currentColor\" stroke-width=\"1.7\" aria-hidden=\"true\"\u003e\u003crect x=\"4\" y=\"4\" width=\"16\" height=\"16\" rx=\"3\"\u003e\u003c\/rect\u003e\u003cpath d=\"m8 12 3 3 5-6\"\u003e\u003c\/path\u003e\u003c\/svg\u003e\u003c\/span\u003e\u003cspan class=\"cg-feature-pill__text\"\u003eAustralian on-site warranty\u003c\/span\u003e\n\u003c\/h3\u003e\n\u003cp\u003eThe supplied Australian model has a 36-month on-site warranty. Ask us about the applicable coverage and service terms.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cfigure style=\"margin:28px 0\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0637\/1554\/1221\/files\/msi-edgexpert-connectx-networking.jpg?v=1792639763\" alt=\"MSI EdgeXpert ConnectX networking illustration; additional systems and cables sold separately\" loading=\"lazy\" style=\"display:block;width:100%;height:auto;border-radius:16px\"\u003e\u003cfigcaption style=\"font-size:14px;color:#536176;margin-top:10px\"\u003eOfficial MSI networking illustration. Additional EdgeXpert systems, QSFP cables and other network equipment shown are sold separately.\u003c\/figcaption\u003e\u003c\/figure\u003e\u003ch2 class=\"cg-section-h2\"\u003eWhere it can fit in your business\u003c\/h2\u003e\n\u003cdiv class=\"cg-feature-grid\"\u003e\n\u003cdiv class=\"cg-feature-item\"\u003e\n\u003ch3\u003eLocal language-model experiments\u003c\/h3\u003e\n\u003cp\u003eEvaluate supported LLMs, compare prompts and test retrieval-augmented generation against your own datasets. Choose model size, quantisation and context length around the available memory.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-feature-item\"\u003e\n\u003ch3\u003eDevelopment and data science\u003c\/h3\u003e\n\u003cp\u003eBuild reproducible workflows with compatible notebooks, frameworks and containers. MSI identifies tools such as PyTorch, Jupyter and Ollama in the platform ecosystem; support varies by release and architecture.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-feature-item\"\u003e\n\u003ch3\u003eEducation and research\u003c\/h3\u003e\n\u003cp\u003eProvide a local platform for hands-on inference, model evaluation and supported fine-tuning experiments. Training capacity depends on model size, method and precision.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-feature-item\"\u003e\n\u003ch3\u003eAI vision and edge development\u003c\/h3\u003e\n\u003cp\u003ePrototype compatible computer-vision and edge-AI applications before a wider deployment. This system is not itself a preconfigured CCTV recorder or a ready-made security analytics licence.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003ch2 class=\"cg-section-h2\"\u003eUnderstanding the AI performance figures\u003c\/h2\u003e\n\u003cp\u003eThe platform is rated at up to \u003cstrong\u003e1 petaFLOP of FP4 sparse AI tensor performance\u003c\/strong\u003e. That is a specific low-precision AI measurement, not an all-purpose speed rating. Model architecture, quantisation, batch size, context length, framework and software versions affect usable performance.\u003c\/p\u003e\n\u003cp\u003eMSI describes a single 128GB system as capable of running models up to 200 billion parameters under supported conditions. A model that fits in memory may still have a different response speed from a smaller model. Share your intended model and workflow with us so the configuration can be checked against the software requirements.\u003c\/p\u003e\n\u003ch2 class=\"cg-section-h2\"\u003eLinux\/Arm software compatibility\u003c\/h2\u003e\n\u003cp\u003eEdgeXpert combines an Arm processor with NVIDIA DGX OS. Verify application binaries, containers, Python packages, drivers and third-party extensions for that platform. A package available for a Windows or x86 Linux workstation does not automatically have an equivalent Arm build.\u003c\/p\u003e\n\u003cp\u003eThe NVIDIA AI software stack supports local development workflows, but application licences, cloud subscriptions and commercial support contracts should be assessed separately. This listing does not include custom AI model deployment, application development or an enterprise software subscription.\u003c\/p\u003e\n\u003cfigure style=\"margin:28px 0\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0637\/1554\/1221\/files\/msi-edgexpert-cooling-design.jpg?v=1792639771\" alt=\"MSI EdgeXpert thermal design illustration\" loading=\"lazy\" style=\"display:block;width:100%;height:auto;border-radius:16px\"\u003e\u003cfigcaption style=\"font-size:14px;color:#536176;margin-top:10px\"\u003eOfficial MSI thermal-design illustration. Keep the chassis ventilation clear and follow the manufacturer’s installation guidance.\u003c\/figcaption\u003e\u003c\/figure\u003e\u003ch2 class=\"cg-section-h2\"\u003ePlan your workspace and setup\u003c\/h2\u003e\n\u003col\u003e\n\u003cli\u003e\n\u003cstrong\u003eConfirm the workload:\u003c\/strong\u003e identify your model, framework, precision, context size and Linux\/Arm dependencies.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003ePrepare connectivity:\u003c\/strong\u003e select a suitable network connection and peripherals. Four built-in USB Type-C ports require an adapter for USB-A-only accessories.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eAllow ventilation:\u003c\/strong\u003e place the system on a stable surface with clear airflow and follow the manufacturer’s power and environmental instructions.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eComplete system setup:\u003c\/strong\u003e follow MSI and NVIDIA documentation, install approved updates and configure user access and backups.\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eValidate with your data:\u003c\/strong\u003e measure the actual workload before committing to a larger rollout or multi-system design.\u003c\/li\u003e\n\u003c\/ol\u003e\n\u003ch2 class=\"cg-section-h2\"\u003eScaling to a second system\u003c\/h2\u003e\n\u003cp\u003eConnectX-7 networking provides a route to larger multi-system experiments. Two units do not become a larger workstation simply by connecting a cable: your topology, interconnect and software must support the intended distributed workload. A second unit, QSFP cable and any switch or deployment services are additional purchases. \u003ca href=\"\/pages\/quote\"\u003eRequest a configuration check or multi-system quote\u003c\/a\u003e.\u003c\/p\u003e\n\u003csection class=\"cg-spec-section\"\u003e\u003ch2 class=\"cg-spec-section__title\" style=\"color:#ffffff!important;font-size:16px!important;line-height:1.3!important;font-weight:600!important;letter-spacing:0!important;text-transform:none!important;padding:6px 24px!important;margin:0!important;min-height:0!important;text-align:left!important\"\u003eTechnical specifications\u003c\/h2\u003e\n\u003cdiv class=\"cg-table-wrap\"\u003e\u003ctable class=\"cg-spec-table\"\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eAustralian manufacturer model\u003c\/th\u003e\n\u003ctd\u003eEdgeXpert-34SAU\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003ePlatform\u003c\/th\u003e\n\u003ctd\u003eNVIDIA DGX Spark \/ NVIDIA GB10 Grace Blackwell\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eCPU\u003c\/th\u003e\n\u003ctd\u003e20-core Arm: 10 Cortex-X925 + 10 Cortex-A725\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eGPU architecture\u003c\/th\u003e\n\u003ctd\u003eNVIDIA Blackwell\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eAI tensor rating\u003c\/th\u003e\n\u003ctd\u003eUp to 1 petaFLOP; FP4 sparse operations; workload-dependent\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eMemory\u003c\/th\u003e\n\u003ctd\u003e128GB LPDDR5x coherent unified system memory\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eMemory interface\u003c\/th\u003e\n\u003ctd\u003e256-bit\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eMemory bandwidth\u003c\/th\u003e\n\u003ctd\u003e273GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eStorage supplied\u003c\/th\u003e\n\u003ctd\u003e4TB NVMe M.2 SSD; PCIe Gen5 Australian configuration\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eOperating system\u003c\/th\u003e\n\u003ctd\u003eNVIDIA DGX OS, based on Ubuntu Linux; Arm architecture\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eUSB connections\u003c\/th\u003e\n\u003ctd\u003e4 × USB Type-C\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eRJ45 network\u003c\/th\u003e\n\u003ctd\u003e1 × 10 Gigabit Ethernet\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eHigh-speed NIC\u003c\/th\u003e\n\u003ctd\u003eNVIDIA ConnectX-7; up to 200GbE platform interface\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eWireless\u003c\/th\u003e\n\u003ctd\u003eWi-Fi 7 and Bluetooth; performance depends on compatible network and region\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eDisplay connection\u003c\/th\u003e\n\u003ctd\u003eHDMI 2.1a\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eAudio output\u003c\/th\u003e\n\u003ctd\u003eHDMI multichannel audio\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eVideo engines\u003c\/th\u003e\n\u003ctd\u003e1 × NVENC and 1 × NVDEC\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eChassis dimensions\u003c\/th\u003e\n\u003ctd\u003e151 × 151 × 52 mm\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eSystem weight\u003c\/th\u003e\n\u003ctd\u003eApproximately 1.2kg; shipping weight is higher\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003ePower\u003c\/th\u003e\n\u003ctd\u003eExternal system power supply; follow the supplied adapter requirements\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eWarranty\u003c\/th\u003e\n\u003ctd\u003e36-month Australian on-site warranty\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003cth scope=\"row\"\u003eBarcode\u003c\/th\u003e\n\u003ctd\u003e4711377403856\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\u003c\/div\u003e\u003c\/section\u003e\u003ch2 class=\"cg-section-h2\"\u003eWhat is included—and what to add\u003c\/h2\u003e\n\u003cp\u003e\u003cstrong\u003eIncluded:\u003c\/strong\u003e one EdgeXpert-34SAU system in the configuration above and its system power supply.\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eOptional:\u003c\/strong\u003e display, keyboard, pointing device, adapters, network cabling, a second system and compatible QSFP interconnect equipment. Manufacturer demonstrations can show multiple systems or additional equipment.\u003c\/p\u003e\n\u003cp\u003eFor a simple wired pointing device, the \u003ca href=\"\/products\/logitech-m90-wired-usb-mouse-910-001795\"\u003eLogitech M90\u003c\/a\u003e can be connected through a suitable \u003ca href=\"\/products\/8ware-usb-c-to-usb-a-male-to-female-adapter-5gbps\"\u003eUSB-C to USB-A adapter\u003c\/a\u003e. Confirm your complete input-device arrangement and application requirements before ordering.\u003c\/p\u003e\n\u003ch2 class=\"cg-section-h2\"\u003eOfficial MSI video\u003c\/h2\u003e\n\u003cdiv style=\"position:relative;aspect-ratio:16\/9;width:100%;margin:20px 0\"\u003e\u003ciframe src=\"https:\/\/www.youtube-nocookie.com\/embed\/PxNZN6kClS8\" title=\"Official MSI EdgeXpert overview\" loading=\"lazy\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture\" allowfullscreen style=\"position:absolute;width:100%;height:100%;border:0;border-radius:16px\"\u003e\u003c\/iframe\u003e\u003c\/div\u003e\n\u003cp\u003eOfficial MSI platform demonstration. Regional configurations, software and optional equipment shown may differ from the EdgeXpert-34SAU supplied here.\u003c\/p\u003e\n\u003ch2 class=\"cg-section-h2\"\u003eOfficial documentation and buying help\u003c\/h2\u003e\n\u003cdiv class=\"cg-download-row\"\u003e\n\u003ca class=\"cg-btn-dark download-link\" href=\"https:\/\/uk.msi.com\/Edge-AI-PC\/EdgeXpert-MS\" target=\"_blank\" rel=\"noopener\"\u003eMSI EdgeXpert overview\u003c\/a\u003e\u003ca class=\"cg-btn-dark download-link\" href=\"https:\/\/docs.nvidia.com\/dgx\/dgx-spark\/\" target=\"_blank\" rel=\"noopener\"\u003eNVIDIA DGX Spark documentation\u003c\/a\u003e\u003ca class=\"cg-btn-dark download-link\" href=\"https:\/\/cctvguru.com.au\/pages\/quote\" target=\"_blank\" rel=\"noopener\"\u003eAsk CCTV Guru about your configuration\u003c\/a\u003e\n\u003c\/div\u003e\n\u003ch2 class=\"cg-section-h2\"\u003eFrequently asked questions\u003c\/h2\u003e\n\u003cdiv class=\"cg-faq-grid\"\u003e\n\u003cdiv class=\"cg-faq-item\"\u003e\n\u003ch3\u003eWhat makes this different from a normal PC?\u003c\/h3\u003e\n\u003cp\u003eEdgeXpert is built for compatible local AI workloads. Its NVIDIA GB10 combines an Arm CPU with a Blackwell GPU and a shared 128GB memory pool. It runs NVIDIA DGX OS, based on Ubuntu Linux. It is intended for developers and technical teams rather than as a drop-in Windows office or gaming PC.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-faq-item\"\u003e\n\u003ch3\u003eWhat does 128GB unified memory mean?\u003c\/h3\u003e\n\u003cp\u003eThe CPU and GPU share one coherent LPDDR5x memory pool. This helps large models use memory without the same separate CPU-RAM and graphics-VRAM split found in many PCs. Operating-system use, model weights, runtime overhead and context cache all consume that pool.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-faq-item\"\u003e\n\u003ch3\u003eCan it run a 200-billion-parameter model?\u003c\/h3\u003e\n\u003cp\u003eMSI describes support for models up to 200B parameters on a 128GB system. This is a workload-dependent capacity claim, not a guarantee for every model, precision or context length. Quantisation, framework support and available working memory determine whether a particular model fits and how fast it runs.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-faq-item\"\u003e\n\u003ch3\u003eIs the advertised petaflop performance available for every task?\u003c\/h3\u003e\n\u003cp\u003eNo. The platform rating is up to 1 petaFLOP for FP4 sparse AI tensor operations. It does not describe general CPU speed, FP32 compute or guaranteed tokens per second. Real performance depends on the model, precision, software and cooling conditions.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-faq-item\"\u003e\n\u003ch3\u003eDoes it run Windows software?\u003c\/h3\u003e\n\u003cp\u003eIt ships with NVIDIA DGX OS on an Arm processor. Check for a supported Linux\/Arm build or compatible container of your application. Standard Windows x86 applications and drivers are not directly interchangeable with this platform.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-faq-item\"\u003e\n\u003ch3\u003eDoes local AI automatically keep everything private?\u003c\/h3\u003e\n\u003cp\u003eLocal inference can keep model processing and data on your own network, but privacy still depends on the applications, update services, external APIs, permissions and network policies you configure. Hardware alone does not certify a deployment as compliant or eliminate all data-transfer risks.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-faq-item\"\u003e\n\u003ch3\u003eCan I connect more than one system?\u003c\/h3\u003e\n\u003cp\u003eThe ConnectX-7 interface supports high-speed multi-system designs. A second system, compatible QSFP interconnect cable, and suitable software configuration are separate. Ask us to confirm the topology and software requirements before ordering a cluster.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-faq-item\"\u003e\n\u003ch3\u003eWhat is included at this price?\u003c\/h3\u003e\n\u003cp\u003eOne Australian EdgeXpert-34SAU system with 128GB unified memory, a 4TB Gen5 NVMe SSD, NVIDIA DGX OS and the system power supply. A monitor, keyboard, mouse, QSFP cable and paid software or deployment services are separate.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-faq-item\"\u003e\n\u003ch3\u003eWhat do I need for the first setup?\u003c\/h3\u003e\n\u003cp\u003ePlan a suitable workspace with ventilation, mains power, network access, and a supported client or local display\/input arrangement. Review the NVIDIA setup documentation and your software requirements before deployment. The built-in USB ports are Type-C; USB-A peripherals need an appropriate adapter.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-faq-item\"\u003e\n\u003ch3\u003eWhat warranty applies?\u003c\/h3\u003e\n\u003cp\u003eThis Australian supplier configuration is listed with a 36-month on-site warranty. Retain your invoice and contact CCTV Guru for warranty assistance and the applicable service terms. On-site warranty is not a promise of a specific response time or included AI software development.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-trust-strip\" style=\"display:flex!important;flex-wrap:wrap!important;align-items:stretch!important;margin:36px 0 0!important;padding:2px!important;border-radius:14px!important\"\u003e\n\u003cdiv class=\"cg-trust-item\" style=\"display:flex!important;flex:1 1 220px!important;align-items:center!important;justify-content:center!important;gap:8px!important;padding:8px 16px!important;min-height:0!important;height:auto!important\"\u003e\n\u003csvg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"20\" height=\"20\" viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"#0875ba\" stroke-width=\"1.7\" stroke-linecap=\"round\" stroke-linejoin=\"round\" aria-hidden=\"true\" style=\"display:block!important;width:20px!important;height:20px!important;min-width:20px!important;flex-shrink:0!important\"\u003e\u003cpath d=\"M12 3 4 6v6c0 5 8 9 8 9s8-4 8-9V6l-8-3Z\"\u003e\u003c\/path\u003e\u003cpath d=\"m8 12 3 3 5-6\"\u003e\u003c\/path\u003e\u003c\/svg\u003e\u003cspan class=\"cg-trust-title\" style=\"font-size:12px!important;line-height:1.5!important;letter-spacing:.04em!important\"\u003e3-year on-site warranty\u003c\/span\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-trust-item\" style=\"display:flex!important;flex:1 1 220px!important;align-items:center!important;justify-content:center!important;gap:8px!important;padding:8px 16px!important;min-height:0!important;height:auto!important\"\u003e\n\u003csvg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"20\" height=\"20\" viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"#0875ba\" stroke-width=\"1.7\" stroke-linecap=\"round\" stroke-linejoin=\"round\" aria-hidden=\"true\" style=\"display:block!important;width:20px!important;height:20px!important;min-width:20px!important;flex-shrink:0!important\"\u003e\u003crect x=\"3\" y=\"5\" width=\"12\" height=\"12\" rx=\"2\"\u003e\u003c\/rect\u003e\u003cpath d=\"M15 9h3l3 4v4h-6M3 17h2m4 0h7\"\u003e\u003c\/path\u003e\u003ccircle cx=\"7\" cy=\"18\" r=\"2\"\u003e\u003c\/circle\u003e\u003ccircle cx=\"18\" cy=\"18\" r=\"2\"\u003e\u003c\/circle\u003e\u003c\/svg\u003e\u003cspan class=\"cg-trust-title\" style=\"font-size:12px!important;line-height:1.5!important;letter-spacing:.04em!important\"\u003eAustralian supply\u003c\/span\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"cg-trust-item\" style=\"display:flex!important;flex:1 1 220px!important;align-items:center!important;justify-content:center!important;gap:8px!important;padding:8px 16px!important;min-height:0!important;height:auto!important\"\u003e\n\u003csvg xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"20\" height=\"20\" viewbox=\"0 0 24 24\" fill=\"none\" stroke=\"#0875ba\" stroke-width=\"1.7\" stroke-linecap=\"round\" stroke-linejoin=\"round\" aria-hidden=\"true\" style=\"display:block!important;width:20px!important;height:20px!important;min-width:20px!important;flex-shrink:0!important\"\u003e\u003cpath d=\"M4 13v-1a8 8 0 0 1 16 0v1\"\u003e\u003c\/path\u003e\u003crect x=\"3\" y=\"11\" width=\"4\" height=\"8\" rx=\"2\"\u003e\u003c\/rect\u003e\u003crect x=\"17\" y=\"11\" width=\"4\" height=\"8\" rx=\"2\"\u003e\u003c\/rect\u003e\u003cpath d=\"M19 19c0 2-3 2-6 2\"\u003e\u003c\/path\u003e\u003c\/svg\u003e\u003cspan class=\"cg-trust-title\" style=\"font-size:12px!important;line-height:1.5!important;letter-spacing:.04em!important\"\u003eCCTV Guru support\u003c\/span\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e","brand":"MSI","offers":[{"title":"Default Title","offer_id":67798852894949,"sku":"EdgeXpert-34SAU","price":11999.0,"currency_code":"AUD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0637\/1554\/1221\/files\/msi-edgexpert-34sau-transparent.png?v=1792641450"}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0637\/1554\/1221\/collections\/msi-edgexpert-34sau-ai-workstation-128gb-4tb.jpg?v=1792639445","url":"https:\/\/cctvguru.com.au\/collections\/ai-computers-workstations.oembed","provider":"CCTV Guru","version":"1.0","type":"link"}