{"product_id":"nvidia-dgx-spark-founders-edition-4tb-ai-supercomputer-with-gb10-chip","title":"NVIDIA DGX Spark Founders Edition 4TB AI Supercomputer with GB10 Chip","description":"\u003cdiv\u003e\n\u003ch1\u003eNVIDIA DGX Spark Founders Edition 4TB Personal AI Supercomputer\u003c\/h1\u003e\n\u003cp\u003eThe \u003cstrong\u003eNVIDIA DGX Spark Founders Edition\u003c\/strong\u003e is a desktop AI supercomputer powered by the revolutionary \u003cstrong\u003eNVIDIA GB10 Grace Blackwell Superchip\u003c\/strong\u003e. Delivering up to \u003cstrong\u003e1 petaFLOP of AI performance\u003c\/strong\u003e in a compact 150mm form factor, this system brings data centre-class AI capabilities directly to your desk. With \u003cstrong\u003e128GB of unified memory\u003c\/strong\u003e, \u003cstrong\u003e4TB of self-encrypting NVMe storage\u003c\/strong\u003e, and the full NVIDIA AI software stack preinstalled, developers and researchers can prototype, fine-tune, and run reasoning AI models with up to 200 billion parameters locally—without relying on cloud resources.\u003c\/p\u003e\n\n\u003ch2\u003eKey Features\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003e1 PetaFLOP AI Performance\u003c\/strong\u003e: Fifth-generation Tensor Cores with FP4 support deliver unprecedented compute power for local AI workloads\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e128GB Unified Memory\u003c\/strong\u003e: LPDDR5x memory shared across CPU and GPU enables models up to 200B parameters (405B when dual units are linked)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e4TB NVMe Storage\u003c\/strong\u003e: Fast, self-encrypting storage with plenty of room for models, datasets, and experiments\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e20-Core Arm Processor\u003c\/strong\u003e: 10 high-performance Cortex-X925 cores and 10 efficiency Cortex-A725 cores running at up to 4GHz\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eCompact \u0026amp; Power-Efficient\u003c\/strong\u003e: Only 1.2kg and 240W—ideal for always-on agent workloads right from your desktop\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eConnectX-7 Networking\u003c\/strong\u003e: Dual QSFP ports supporting 200Gbps for clustering multiple DGX Spark units together\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch2\u003eBuilt for Local AI Development\u003c\/h2\u003e\n\u003cp\u003eUnlike traditional GPUs with hard VRAM limits, the \u003cstrong\u003eDGX Spark's unified memory architecture\u003c\/strong\u003e powered by NVLink-C2C makes the entire 128GB accessible to both CPU and GPU with 273GB\/s bandwidth—5 times faster than PCIe Gen 5. This allows you to \u003cstrong\u003efine-tune models up to 70 billion parameters\u003c\/strong\u003e and run inference on the latest generation of reasoning models from DeepSeek, Meta, Google, Qwen, and NVIDIA without cloud dependence. Perfect for AI researchers, data scientists, and developers building edge applications, robotics solutions, and local autonomous agents.\u003c\/p\u003e\n\n\u003ch2\u003eGrace Blackwell GB10 Superchip\u003c\/h2\u003e\n\u003cp\u003eAt the heart of DGX Spark is the \u003cstrong\u003eNVIDIA GB10 Grace Blackwell Superchip\u003c\/strong\u003e, a system-on-chip featuring an integrated Blackwell GPU with fifth-generation Tensor Cores, fourth-generation RT Cores, and a powerful 20-core Arm Grace CPU. This combination delivers desktop-level AI supercomputing with support for modern frameworks including NVIDIA Isaac, Metropolis, Holoscan, and more.\u003c\/p\u003e\n\n\u003ch2\u003eComplete AI Software Stack\u003c\/h2\u003e\n\u003cp\u003eShips with \u003cstrong\u003eNVIDIA DGX OS\u003c\/strong\u003e (Ubuntu 24.04-based) and the complete NVIDIA AI software stack preinstalled. Includes streamlined access to state-of-the-art open models, TensorRT-LLM optimizations, and tools for building autonomous agents with NVIDIA OpenShell. Software updates deliver continuous performance improvements—recent updates have shown up to 2.5× inference speedups and 8× faster video generation.\u003c\/p\u003e\n\n\u003ch2\u003eUniversal Connectivity\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eNetworking\u003c\/strong\u003e: 10GbE RJ-45 Ethernet, ConnectX-7 SmartNIC with dual QSFP 200Gbps ports, Wi-Fi 7, Bluetooth 5.4\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eI\/O\u003c\/strong\u003e: 4× USB Type-C ports, 1× HDMI 2.1a with multichannel audio\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eClustering\u003c\/strong\u003e: Link two DGX Spark systems via ConnectX-7 for 256GB combined memory and up to 8TB total storage\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch2\u003eFounders Edition Exclusive\u003c\/h2\u003e\n\u003cp\u003eThe \u003cstrong\u003eFounders Edition\u003c\/strong\u003e features a premium gold metal chassis and comes with \u003cstrong\u003e4TB of storage\u003c\/strong\u003e—double the capacity of many partner configurations. This limited-edition release offers the most direct relationship with NVIDIA's DGX OS documentation and is the simplest choice for those who want NVIDIA's own reference DGX Spark system.\u003c\/p\u003e\n\n\u003ch2\u003eWhat's in the Box\u003c\/h2\u003e\n\u003cul\u003e\n\u003cli\u003eNVIDIA DGX Spark Founders Edition (gold chassis)\u003c\/li\u003e\n\u003cli\u003e240W power adapter\u003c\/li\u003e\n\u003cli\u003ePower cable\u003c\/li\u003e\n\u003cli\u003eQuick start guide\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch2\u003eFull Specifications\u003c\/h2\u003e\n\n\u003ch3\u003eCompute\u003c\/h3\u003e\n\u003ctable\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eSuperchip\u003c\/td\u003e\n\u003ctd\u003eNVIDIA GB10 Grace Blackwell Superchip\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eGPU Architecture\u003c\/td\u003e\n\u003ctd\u003eNVIDIA Blackwell with 5th Generation Tensor Cores, 4th Generation RT Cores\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCPU\u003c\/td\u003e\n\u003ctd\u003e20-core Arm processor (10× Cortex-X925 performance cores + 10× Cortex-A725 efficiency cores)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eAI Performance\u003c\/td\u003e\n\u003ctd\u003eUp to 1 petaFLOP (FP4 precision)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMemory\u003c\/td\u003e\n\u003ctd\u003e128GB LPDDR5x unified system memory, 256-bit interface, 4266MHz, 273GB\/s bandwidth\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\n\n\u003ch3\u003eStorage \u0026amp; Operating System\u003c\/h3\u003e\n\u003ctable\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eStorage\u003c\/td\u003e\n\u003ctd\u003e4TB NVMe M.2 SSD with self-encryption\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eOperating System\u003c\/td\u003e\n\u003ctd\u003eNVIDIA DGX OS (Ubuntu 24.04-based)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\n\n\u003ch3\u003eNetworking \u0026amp; Connectivity\u003c\/h3\u003e\n\u003ctable\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eEthernet\u003c\/td\u003e\n\u003ctd\u003e1× RJ-45 10GbE\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eSmartNIC\u003c\/td\u003e\n\u003ctd\u003eConnectX-7 with 2× QSFP ports (200Gbps each)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eWireless\u003c\/td\u003e\n\u003ctd\u003eWi-Fi 7, Bluetooth 5.4\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eUSB\u003c\/td\u003e\n\u003ctd\u003e4× USB Type-C\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDisplay\u003c\/td\u003e\n\u003ctd\u003e1× HDMI 2.1a with multichannel audio\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\n\n\u003ch3\u003eVideo Processing\u003c\/h3\u003e\n\u003ctable\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eEncode\/Decode\u003c\/td\u003e\n\u003ctd\u003e1× NVENC, 1× NVDEC\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\n\n\u003ch3\u003ePhysical Specifications\u003c\/h3\u003e\n\u003ctable\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eForm Factor\u003c\/td\u003e\n\u003ctd\u003eSmall form factor (SFF) mini PC\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDimensions\u003c\/td\u003e\n\u003ctd\u003e150mm (W) × 150mm (D) × 50.5mm (H)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eWeight\u003c\/td\u003e\n\u003ctd\u003e1.2kg (2.65 lbs)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eChassis\u003c\/td\u003e\n\u003ctd\u003eGold metal (Founders Edition exclusive)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\n\n\u003ch3\u003ePower \u0026amp; Environment\u003c\/h3\u003e\n\u003ctable\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003ePower Supply\u003c\/td\u003e\n\u003ctd\u003e240W adapter\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eOperating Temperature\u003c\/td\u003e\n\u003ctd\u003e5°C to 30°C (41°F to 86°F)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eOperating Humidity\u003c\/td\u003e\n\u003ctd\u003e10% to 90% (non-condensing)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eOperating Altitude\u003c\/td\u003e\n\u003ctd\u003eUp to 3,000 meters (9,843 feet)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\n\n\u003ch3\u003eAI Capabilities\u003c\/h3\u003e\n\u003ctable\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eModel Support (Inference)\u003c\/td\u003e\n\u003ctd\u003eUp to 200B parameters (single unit), up to 405B parameters (dual unit cluster)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eModel Support (Fine-tuning)\u003c\/td\u003e\n\u003ctd\u003eUp to 70B parameters\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eClustering\u003c\/td\u003e\n\u003ctd\u003e2+ units via ConnectX-7 for expanded memory and storage\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\n\n\u003cp\u003e\u003cem\u003eSpecifications are sourced from the official manufacturer product page and may be updated.\u003c\/em\u003e\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Nvidia","offers":[{"title":"Default Title","offer_id":44324933959758,"sku":"PA-NVIDIADGXSPARKFOU","price":16800.0,"currency_code":"AUD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0676\/3134\/9838\/files\/Spark_x2_1c260908-ef8b-4acb-a3c3-aade73a28102.jpg?v=1789260783","url":"https:\/\/projectorsaustralia.com.au\/products\/nvidia-dgx-spark-founders-edition-4tb-ai-supercomputer-with-gb10-chip","provider":"Projectors Australia","version":"1.0","type":"link"}