{"product_id":"nvidia-dgx-spark-4tb-desktop-ai-supercomputer","title":"NVIDIA DGX Spark 4TB Desktop AI Supercomputer","description":"\u003ch2\u003e\u003cspan style=\"text-decoration: underline; color: rgb(0, 0, 0);\"\u003e\u003cstrong\u003eFeatures of NVIDIA DGX Spark 4TB Desktop AI Supercomputer\u003c\/strong\u003e\u003c\/span\u003e\u003c\/h2\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e\u003cstrong\u003eNVIDIA DGX Spark Designed to build and run autonomous agents.\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e\u003cstrong\u003eDesktop Agent Computer\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\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\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e\u003cstrong\u003eRun Autonomous Agents More Safely\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eNVIDIA Agent Toolkit with NVIDIA OpenShell provides open source models and software for developers to build and deploy safer autonomous agents. NVIDIA NemoClaw is an open sourcr reference stack that adds security and privacy guardrails to OpenClaw using OpenShell. (\u003cstrong\u003eFor More Information Visit the Official Brand Website\u003c\/strong\u003e)\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e\u003cstrong\u003ePlaybooks for Everyone\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eFrom novice to expert, leverage our curated playbooks to get off to a running start on various projects. Playbooks contain step-by-step recipes to demonstrate the art of the possible. (\u003cstrong\u003eFor More Information Visit the Official Brand Website\u003c\/strong\u003e)\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e\u003cstrong\u003eNVIDIA GB10 Superchip\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eExperience up to 1 petaFLOP  of AI performance at FP4 precision with the NVIDIA Grace Blackwell architecture.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e\u003cstrong\u003e128 GB of Coherent Unified System Memory\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eRun AI development and testing workloads with AI models up to 200 billion parameters at your desktop with a large, unified system memory.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e\u003cstrong\u003eNVIDIA ConnectX Networking\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\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\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e\u003cstrong\u003eNVIDIA AI Software Stack\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eUtilize a full-stack solution for generative AI workloads, encompassing NVIDIA tools, frameworks, libraries, and pre-trained models including NVIDIA NIM.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e\u003cstrong\u003eAccelerate All Agentic AI Workloads\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\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\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e\u003cstrong\u003eDevelop, test, and validate AI models and applications.\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eWith the NVIDIA AI software stack, NVIDIA DGX Spark provides a platform for developers to create, test, and validate AI models, as well as build AI agents, AI-augmented applications, and solutions. For final tuning or deployment, conveniently evaluate the work for eventual migration to the NVIDIA DGX cloud or other NVIDIA-accelerated data centers or cloud infrastructures.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e\u003cstrong\u003eFine-tune AI models up to 70 billion parameters.\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eImprove the performance of pre-trained models by fine-tuning on NVIDIA DGX Spark. With 128 GB of unified system memory, fine-tune models up to 70 billion parameters to customize AI models and solutions for specific needs and use cases.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e\u003cstrong\u003eTest, validate, and inference with AI models up to 200 billion parameters.\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eFifth-generation Tensor Cores with support for FP4 deliver up to 1 petaFLOP of AI computing performance, combined with 128 GB of system memory, accelerating inference of state-of-the-art AI models to test, validate, and deploy from your NVIDIA DGX Spark.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e\u003cstrong\u003eHigh-performance data science at your desk.\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eNVIDIA DGX Spark’s combination of 128 GB of unified memory and 1 PetaFLOP of parallel throughput maximizes performance of large, computationally complex data analytics and machine learning workflows at your desk.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e\u003cstrong\u003eDevelop edge applications with NVIDIA AI frameworks, including NVIDIA Isaac, Metropolis, and many others.\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eNVIDIA DGX Spark offers an exceptional platform for developing robotics, smart city, and computer vision solutions. NVIDIA frameworks include Isaac, Metropolis, and Holoscan, enabling developers to leverage the power of NVIDIA DGX Spark to develop edge applications quickly.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003ch2\u003e\u003cspan style=\"text-decoration: underline; color: rgb(0, 0, 0);\"\u003e\u003cstrong\u003eSpecifications of NVIDIA DGX Spark 4TB Desktop AI Supercomputer\u003c\/strong\u003e\u003c\/span\u003e\u003c\/h2\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003ctable xmlns=\"http:\/\/www.w3.org\/1999\/xhtml\" cellspacing=\"0\" cellpadding=\"0\" dir=\"ltr\" border=\"1\" data-sheets-root=\"1\" data-sheets-baot=\"1\"\u003e\n\u003ccolgroup\u003e\n\u003ccol width=\"249\"\u003e\n\u003ccol width=\"408\"\u003e\n\u003c\/colgroup\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eArchitecture\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eNVIDIA Grace Blackwell\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eGPU\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eBlackwell Architecture\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eCPU\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e20-core Arm, 10 Cortex-X925 + 10 Cortex-A725 Arm\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eCUDA Cores\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eBlackwell Generation\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eTensor Cores\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e5th Generation\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eRT Cores\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e4th Generation\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eTensor Performance\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eUp to 1 PFLOP FP4\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eSystem Memory\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e128 GB LPDDR5x, coherent unified system memory\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eMemory Interface\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e256-bit\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eMemory Bandwidth\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e273 GB\/s\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eStorage\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e4 TB NVME.M2 with self-encryption\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eUSB\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e4x USB TypeC\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eEthernet\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e1x RJ-45 connector \/ 10 GbE\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eNIC\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eConnectX-7 NIC @ 200 Gbps\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eWi-Fi\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eWiFi 7\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eBluetooth\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eBT 5.4\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eAudio-output\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eHDMI multichannel audio output\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003ePower Supply\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e240 Watts\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eGB10 TDP\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e140 W\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eDisplay Connectors\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e1x HDMI 2.1a, Up to 3x DisplayPort over USB-C (DP Alt Mode)\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eNVENC | NVDEC\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e1x | 1x\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eOS\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eNVIDIA DGX OS\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eSystem Dimensions\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e150 mm L x 150 mm W x 50.5 mm H\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eWarranty\u003c\/span\u003e\u003c\/td\u003e\n\u003ctd\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e1 Year\u003c\/span\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e","brand":"Nvidia","offers":[{"title":"Default Title","offer_id":67896926961757,"sku":"940-54242-0008-000","price":767000.0,"currency_code":"INR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0591\/4220\/9629\/files\/940-54242-0008-000-image-main.webp?v=1793617344","url":"https:\/\/elitehubs.com\/products\/nvidia-dgx-spark-4tb-desktop-ai-supercomputer","provider":"EliteHubs","version":"1.0","type":"link"}