{"product_id":"nvidia-dgx-spark-ai-workstation","title":"NVIDIA DGX Spark GB10 Grace Blackwell Desktop AI Supercomputer with 128GB Unified Memory 4TB NVME with self-encryption","description":"\u003cstyle\u003e\na {\n    text-decoration: none;\n    color: #464feb;\n}\ntr th, tr td {\n    border: 1px solid #e6e6e6;\n}\ntr th {\n    background-color: #f5f5f5;\n}\n\u003c\/style\u003e\n\u003cdiv\u003e⚡ \u003cstrong\u003eGrace‑Blackwell Superchip Performance\u003c\/strong\u003e – Powered by NVIDIA GB10 delivering up to \u003cstrong\u003e1 PFLOP FP4 AI compute\u003c\/strong\u003e for next‑gen model training. \u003cbr\u003e\u003cbr\u003e🧠 \u003cstrong\u003e128GB Unified LPDDR5X Memory\u003c\/strong\u003e – Seamless CPU‑GPU memory pooling enables running models up to \u003cstrong\u003e200B parameters\u003c\/strong\u003e locally. \u003cbr\u003e\u003cbr\u003e💻 \u003cstrong\u003eDesktop AI Supercomputer\u003c\/strong\u003e – Compact workstation form factor bringing datacenter‑class AI development to your desk. \u003cbr\u003e\u003cbr\u003e🔗 \u003cstrong\u003eNVLink‑C2C High‑Bandwidth Coherency\u003c\/strong\u003e – 5× PCIe Gen5 bandwidth for accelerated tuning, inference \u0026amp; data orchestration. \u003cbr\u003e\u003cbr\u003e🌐 \u003cstrong\u003eConnectX Networking Support\u003c\/strong\u003e – Link two DGX Sparks to handle \u003cstrong\u003e405B‑parameter models\u003c\/strong\u003e and scale AI workloads. \u003cbr\u003e\u003cbr\u003e🛠️ \u003cstrong\u003eNVIDIA AI Software Stack Pre‑Loaded\u003c\/strong\u003e – DGX OS, PyTorch, Jupyter, Ollama \u0026amp; NIM ready out‑of‑box for frictionless deployment.\u003cbr\u003e\u003cbr\u003e\u003cmeta http-equiv=\"Content-Type\" content=\"text\/html; charset=us-ascii\"\u003e\n\u003c\/div\u003e\n\u003cstyle\u003e\na {\n    text-decoration: none;\n    color: #464feb;\n}\ntr th, tr td {\n    border: 1px solid #e6e6e6;\n}\ntr th {\n    background-color: #f5f5f5;\n}\n\u003c\/style\u003e\n\u003cdiv\u003e\n\u003cdiv\u003eNVIDIA DGX Spark is a compact desktop AI supercomputer powered by the Grace Blackwell GB10 Superchip, delivering up to 1 PFLOP FP4 performance for advanced AI workflows. With 128GB unified memory and NVLink‑C2C high‑speed coherency, it enables local prototyping, fine‑tuning, and inference of models up to 200B parameters. Preloaded with NVIDIA’s optimized AI software stack, DGX Spark empowers developers, researchers, and enterprises to build, test, and scale next‑generation AI solutions from their desktop.\u003cbr\u003e\u003cbr\u003e\u003cstrong\u003eProduct Specifications:\u003cbr\u003e\u003cbr\u003e\u003c\/strong\u003e\n\u003c\/div\u003e\n\u003cmeta http-equiv=\"Content-Type\" content=\"text\/html; charset=us-ascii\"\u003e\n\u003c\/div\u003e\n\u003cstyle\u003e\na {\n    text-decoration: none;\n    color: #464feb;\n}\ntr th, tr td {\n    border: 1px solid #e6e6e6;\n}\ntr th {\n    background-color: #f5f5f5;\n}\n\u003c\/style\u003e\n\u003cdiv\u003e\n\u003cdiv\u003e\n\u003ctable height=\"740\" style=\"width: 100.059%; height: 579.983px;\"\u003e\n\u003ctbody\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eArchitecture\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003eNVIDIA Grace Blackwell\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eGPU\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003eNVIDIA Blackwell Architecture\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eCPU\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003e20 core Arm (10 Cortex-X925 + 10 Cortex-A725)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eCUDA Cores\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003eNVIDIA Blackwell Generation\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eTensor Cores\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003e5th Generation\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eRT Cores\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003e4th Generation\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eTensor Performance\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003e1 PFLOP\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eSystem Memory\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003e128 GB LPDDR5x coherent unified system memory\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eMemory Interface\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003e256-bit\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eMemory Bandwidth\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003eUp to 273 GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eStorage\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003e4 TB NVMe M.2 with self-encryption\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eUSB\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003e4x USB Type-C\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eEthernet\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003e1x RJ-45 connector 10 GbE\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eNIC\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003eConnectX-7 NIC @ 200 Gbps\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eWi-Fi\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003eWiFi 7\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eBluetooth\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003eBT 5.4 with LE\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eAudio-output\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003eHDMI multichannel audio output\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003ePower Supply\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003e240 W\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eGB10 TDP\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003e140 W\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eDisplay Connectors\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003e1x HDMI 2.1a\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eNVENC\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003e1x\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eNVDEC\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003e1x\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eOS\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003eNVIDIA DGX OS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eSystem Dimensions\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003e150 mm L x 150 mm W x 50.5 mm H\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.2917px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.2917px;\"\u003eSystem Weight\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.2917px;\"\u003e1.2 kg\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 22.691px;\"\u003e\n\u003ctd style=\"width: 32.1747%; height: 22.691px;\"\u003eWarranty\u003c\/td\u003e\n\u003ctd style=\"width: 67.3472%; height: 22.691px;\"\u003e3 Years by Brand \u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003c\/div\u003e\n\u003cbr\u003e\n\u003c\/div\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":54986326933807,"sku":"NVIDIA-DGX-Spark","price":522999.0,"currency_code":"INR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/1780\/7915\/files\/NVIDIA_DGX_Spark_GB10_Grace_Blackwell_Desktop_AI_Supercomputer_with_128GB_Unified_Memory-tpstech.in.webp?v=1773128467","url":"https:\/\/www.tpstech.in\/products\/nvidia-dgx-spark-ai-workstation","provider":"tpstech.in","version":"1.0","type":"link"}