{"product_id":"nvidia-dgx-spark","title":"NVIDIA DGX Spark","description":"\u003cblockquote\u003e\n\u003ch2 style=\"text-align: center;\"\u003eNVIDIA DGX Spark\u003c\/h2\u003e\n\u003c\/blockquote\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cspan style=\"color: rgb(123, 194, 61);\"\u003e\u003cstrong\u003eA Grace Blackwell AI supercomputer on your desk.\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003ePowered by the NVIDIA GB10 Grace Blackwell Superchip, NVIDIA DGX™ Spark delivers one petaFLOP1 of AI performance in a power-efficient, compact form factor. With the NVIDIA AI software stack preinstalled and 128 GB of memory, developers can prototype, fine-tune, and inference the latest generation of reasoning AI models from DeepSeek, Meta, NVIDIA, Google, Qwen and others with up to 200 billion parameters locally.\u003c\/p\u003e\n\u003cblockquote\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cspan style=\"color: rgb(255, 42, 0);\"\u003eBuy either single or dual with free certified QSFP56 Cable (0.5m). Delivery starts from January 25, 2026 - buy yours today.\u003c\/span\u003e\u003c\/p\u003e\n\u003c\/blockquote\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0014\/4313\/5560\/files\/SPARK-FRONT_b0e25269-39ba-404a-a0b0-824871b9fc0a.png?v=1763456331\" alt=\"\"\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003ch2 style=\"text-align: center;\"\u003eFeatures\u003c\/h2\u003e\n\u003ch3 style=\"text-align: center;\"\u003eNVIDIA GPU, CPU, Networking, and AI Software Technologies\u003c\/h3\u003e\n\u003ctable style=\"border-collapse: collapse; width: 100%; height: 195.938px;\"\u003e\n\u003ctbody\u003e\n\u003ctr style=\"height: 97.9688px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 97.9688px; text-align: center;\"\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0014\/4313\/5560\/files\/m48-gh200-ffffff_1.svg?v=1763450000\" alt=\"\" width=\"80\" height=\"80\"\u003e\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003eNVIDIA GB10 Superchip\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp\u003eExperience up to  1 petaFLOP  of AI performance at FP4 precision with the NVIDIA Grace Blackwell architecture.\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 97.9688px; text-align: center;\"\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0014\/4313\/5560\/files\/m48-ram-memory-ffffff_1.svg?v=1763450000\" alt=\"\" width=\"80\" height=\"80\"\u003e\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cstrong\u003e128 GB of Coherent Unified System Memory\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp\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\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 97.9688px; text-align: center;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 97.9688px;\"\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cimg style=\"display: block; margin-left: auto; margin-right: auto;\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0014\/4313\/5560\/files\/m48-cx-7-chip-ffffff_1.svg?v=1763449999\" alt=\"\" width=\"80\" height=\"80\"\u003e\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cstrong\u003eNVIDIA ConnectX Networking\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\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\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 97.9688px;\"\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cimg style=\"display: block; margin-left: auto; margin-right: auto;\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0014\/4313\/5560\/files\/m48-nim-ffffff_2.svg?v=1763450000\" alt=\"\" width=\"80\" height=\"80\"\u003e\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cstrong\u003eNVIDIA AI Software Stack\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\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\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003ch2 style=\"text-align: center;\"\u003eWorkloads\u003c\/h2\u003e\n\u003ch3 style=\"text-align: center;\"\u003eAccelerate All AI Workloads\u003c\/h3\u003e\n\u003cp style=\"text-align: center;\"\u003eDelivering the power of an AI supercomputer in a desktop-friendly size, NVIDIA DGX Spark is ideal for AI developer, researcher, and data scientist workloads.\u003c\/p\u003e\n\u003ctable style=\"border-collapse: collapse; width: 100%;\"\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; width: 100%;\" colspan=\"2\"\u003e\n\u003ch4 style=\"text-align: center;\"\u003e\u003cspan style=\"color: rgb(123, 194, 61);\"\u003ePrototyping\u003c\/span\u003e\u003c\/h4\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cstrong\u003eDevelop, test, and validate AI models and applications.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003eWith the NVIDIA AI software stack, NVIDIA DGX Spark provides the platform for developers to create, test, and validate AI models and AI-augmented applications and solutions. For final tuning or deployment, conveniently evaluate work for eventual migration to NVIDIA DGX cloud or other NVIDIA accelerated data centers or cloud infrastructures.\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; width: 50%;\"\u003e\n\u003ch4 style=\"text-align: center;\"\u003e\u003cspan style=\"color: rgb(123, 194, 61);\"\u003eFine-Tuning\u003c\/span\u003e\u003c\/h4\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cstrong\u003eFine-tune AI models up to 70 billion parameters.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003eImprove the performance of pre-trained models by fine-tuning on NVIDIA DGX Spark. With 128GB 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\/p\u003e\n\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; width: 50%;\"\u003e\n\u003ch4 style=\"text-align: center;\"\u003e\u003cspan style=\"color: rgb(123, 194, 61);\"\u003eInference\u003c\/span\u003e\u003c\/h4\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cstrong\u003eTest, validate, and inference with AI models.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003eFifth-generation Tensor Cores with support for FP4 deliver up to 1 petaFLOP of AI computing performance, combined with 128GB of system memory, accelerate inference of state-of-the-art AI models to test, validate and deploy from your NVIDIA DGX Spark.\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; width: 50%;\"\u003e\n\u003ch4 style=\"text-align: center;\"\u003e\u003cspan style=\"color: rgb(123, 194, 61);\"\u003eData Science\u003c\/span\u003e\u003c\/h4\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cstrong\u003eHigh-performance data science at your desk.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003eNVIDIA DGX Spark’s combination of 128GB 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\/p\u003e\n\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; width: 50%;\"\u003e\n\u003ch4 style=\"text-align: center;\"\u003e\u003cspan style=\"color: rgb(123, 194, 61);\"\u003eEdge Applications\u003c\/span\u003e\u003c\/h4\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cstrong\u003eDevelop edge applications with NVIDIA AI frameworks.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003eNVIDIA DGX Spark offers an exceptional platform for developing robotics, smart city, and computer vision solutions. NVIDIA frameworks include Isaac, Metropolis, and Holoscan. These frameworks and tools enable developers to take advantage of the power of NVIDIA DGX Spark to quickly develop edge applications.\u003c\/p\u003e\n\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003ch2 style=\"text-align: center;\"\u003eNVIDIA DGX Spark Software\u003c\/h2\u003e\n\u003cp style=\"text-align: center;\"\u003eNVIDIA DGX Spark software stack accelerates AI and deep learning workloads while streamlining prototyping and development. It provides a scalable foundation for AI initiatives, enabling developers to harness NVIDIA’s powerful infrastructure to drive innovation and achieve transformative results.\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003ca rel=\"noopener\" href=\"https:\/\/developer.nvidia.com\/topics\/ai\/dgx-spark\" target=\"_blank\"\u003eLearn More \u0026gt;\u003c\/a\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003ch2 style=\"text-align: center;\"\u003eSignificant Features and Benefits\u003c\/h2\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0014\/4313\/5560\/files\/webp_nvidia_project_digits_exploded_vew.jpg?v=1763450172\" alt=\"\"\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003ch2 style=\"text-align: center;\"\u003eA Grace Blackwell AI supercomputer on Your Desk\u003c\/h2\u003e\n\u003ch4 style=\"text-align: center;\"\u003e1. Based on NVIDIA Grace Blackwell Architecture\u003c\/h4\u003e\n\u003cp style=\"text-align: center;\"\u003eAt the heart of DGX Spark is the new GB10 Grace Blackwell Superchip, based on the Grace Blackwell architecture and optimized for a desktop form factor. GB10 features a powerful Blackwell GPU with fifth-generation Tensor Cores and FP4 support, delivering up to 1000 AI TOPS of compute. GB10 also includes a high-performance Grace 20-core Arm CPU to supercharge data preprocessing and orchestration, speeding up model tuning and real-time inferencing. The GB10 Superchip uses the NVLink™-C2C to deliver a CPU+GPU coherent memory model with 5X the bandwidth of PCIe Gen 5.\u003c\/p\u003e\n\u003ch4 style=\"text-align: center;\"\u003e2. Work With the Latest Generation of Large-Parameter Generative AI Models\u003c\/h4\u003e\n\u003cp style=\"text-align: center;\"\u003eWith 128 GB of unified system memory and support for the FP4 data format, DGX Spark can support AI models of up to 200B parameters, enabling AI developers to prototype, fine-tune and inference the latest generation of AI reasoning models—such as DeepSeek R1 distilled versions up to 70 billion parameters—on their desktop. With built-in NVIDIA ConnectX™ network technology, two DGX Spark systems can be connected to work on even larger models such as Llama 3.1 405B.\u003c\/p\u003e\n\u003ch4 style=\"text-align: center;\"\u003e3. Develop Locally, Deploy Anywhere at Scale\u003c\/h4\u003e\n\u003cp style=\"text-align: center;\"\u003eDGX Spark provides developers with a powerful, experimentation ground for prototyping models and AI applications, freeing up valuable compute resources in their cluster environments better suited for training and deploying production models. Leveraging the NVIDIA AI platform software architecture makes it possible for DGX Spark users to seamlessly move their models from their desktop to DGX Cloud or any accelerated cloud or data center infrastructure with virtually no code changes, making it easier than ever to prototype, fine-tune, and iterate.\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003ch2 style=\"text-align: center;\"\u003eSpecifications\u003c\/h2\u003e\n\u003ctable style=\"border-collapse: collapse; width: 100%;\"\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eArchitecture\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003eNVIDIA Grace Blackwell\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eGPU\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003eBlackwell Architecture\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eCPU\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003e20 core Arm, 10 Cortex-X925 + 10 Cortex-A725 Arm\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eCUDA Cores\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003eBlackwell Generation\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eTensor Cores\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003e5th Generation\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eRT Cores\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003e4th Generation\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eTensor Performance\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003e1 PFLOP\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eSystem Memory\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003e128 GB LPDDR5x, coherent unified system memory\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eMemory Interface\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003e256-bit\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eMemory Bandwidth\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003e273 GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eStorage\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003e4 TB NVME.M2 with self-encryption\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eUSB\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003e4x USB TypeC\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eEthernet\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003e1x RJ-45 connector, 10 GbE\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eNIC\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003eConnectX-7 NIC @ 200 Gbps\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eWi-Fi\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003eWiFi 7\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eBluetooth\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003eBT 5.4\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eAudio-output\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003eHDMI multichannel audio output\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003ePower Supply\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003e240 Watts\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eDisplay Connectors\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003e1x HDMI 2.1a\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eNVENC | NVDEC\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003e1x | 1x\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eOS\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003eNVIDIA DGX™ OS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eSystem Dimensions\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003e150 mm L × 150 mm W × 50.5 mm H\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 50.1598%;\"\u003eSystem Weight\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center; width: 49.8402%;\"\u003e1.2 kg\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cem\u003e* preliminary specifications, subject to change. 1 Theoretical FP4 TOPS using the sparsity feature.\u003c\/em\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003ch2 style=\"text-align: center;\"\u003eResources\u003c\/h2\u003e\n\u003ctable style=\"border-collapse: collapse; width: 100%;\"\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center;\"\u003eDatasheet\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; text-align: center;\"\u003e\u003ca rel=\"noopener\" href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0014\/4313\/5560\/files\/workstation-datasheet-dgx-spark-gtc25-spring-nvidia-us-3716899-web.pdf?v=1763452160\" target=\"_blank\"\u003eDownload\u003c\/a\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003ch2 style=\"text-align: center;\"\u003ePackage Contains\u003c\/h2\u003e\n\u003ctable style=\"border-collapse: collapse; width: 100%; height: 49.1876px;\"\u003e\n\u003ctbody\u003e\n\u003ctr style=\"height: 19.5938px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5938px; text-align: center;\"\u003eNVIDIA® DGX Spark™\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5938px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5938px; text-align: center;\"\u003eQuick Start Card\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 10px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 10px; text-align: center;\"\u003eSupport Card\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 0px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 0px; text-align: center;\"\u003ePower Supply\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cbr\u003e\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Single Unit","offer_id":51141865308477,"sku":"SBC1142","price":549999.99,"currency_code":"INR","in_stock":true},{"title":"Dual Unit with 200G QSFP56 Cable","offer_id":51141865341245,"sku":"SBC1142-D","price":1110999.99,"currency_code":"INR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0014\/4313\/5560\/files\/SPARK-3QTR-Right.png?v=1763456416","url":"https:\/\/thinkrobotics.com\/ar\/products\/nvidia-dgx-spark","provider":"Atlantis Robotics","version":"1.0","type":"link"}