{"product_id":"nvidia-dgx-spark-personal-ai-supercomputer-gb10-grace-blackwell-128gb-unified-memory-4tb-ssd","title":"NVIDIA DGX Spark Personal AI Supercomputer – GB10 Grace Blackwell, 128GB Unified Memory, 4TB SSD","description":"\u003ch2\u003eNVIDIA DGX Spark\u003c\/h2\u003e\n\u003cp\u003eA Grace Blackwell AI supercomputer for your desk. Built on the NVIDIA GB10 Grace Blackwell Superchip, DGX Spark is a complete local AI platform for developers, researchers, data scientists and students — run, fine-tune and deploy large AI models and always-on agents without depending on the cloud.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cstrong\u003eNVIDIA GB10 Superchip\u003c\/strong\u003e – Blackwell GPU with 5th Gen Tensor Cores and a 20-core Arm CPU, up to 1 petaFLOP of FP4 AI performance\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003e128 GB coherent unified system memory\u003c\/strong\u003e – inference on models up to 200 billion parameters and fine-tuning of models up to 70 billion parameters\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNVIDIA ConnectX-7 networking\u003c\/strong\u003e – cluster up to four DGX Spark systems for larger models (two systems: up to 400B parameters)\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNVIDIA AI software stack preinstalled\u003c\/strong\u003e – DGX OS (Ubuntu-based), CUDA, NIM microservices, NeMo, RAPIDS, Blueprints, plus PyTorch and Jupyter support\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eNVIDIA Sync\u003c\/strong\u003e – connect from your laptop to monitor the system and launch VS Code, Cursor or AI Workbench remotely\u003c\/li\u003e\n\u003cli\u003e\n\u003cstrong\u003eCompact desktop design\u003c\/strong\u003e – 150 x 150 x 50.5 mm, 1.2 kg, 240 W power supply\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003ch3\u003eSpecifications\u003c\/h3\u003e\n\u003ctable\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003ePart Number\u003c\/td\u003e\n\u003ctd\u003e940-54242-0000-000\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eArchitecture\u003c\/td\u003e\n\u003ctd\u003eNVIDIA Grace Blackwell\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eSuperchip\u003c\/td\u003e\n\u003ctd\u003eNVIDIA GB10 Grace Blackwell\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eGPU\u003c\/td\u003e\n\u003ctd\u003eBlackwell Architecture\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCPU\u003c\/td\u003e\n\u003ctd\u003e20-core Arm, 10 Cortex-X925 + 10 Cortex-A725 Arm\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eCUDA Cores\u003c\/td\u003e\n\u003ctd\u003eBlackwell Generation (6,144)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eTensor Cores\u003c\/td\u003e\n\u003ctd\u003e5th Generation\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eRT Cores\u003c\/td\u003e\n\u003ctd\u003e4th Generation\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eTensor Performance\u003c\/td\u003e\n\u003ctd\u003eUp to 1 PFLOP FP4 (theoretical, with sparsity)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eSystem Memory\u003c\/td\u003e\n\u003ctd\u003e128 GB LPDDR5x, coherent unified system memory\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMemory Interface\u003c\/td\u003e\n\u003ctd\u003e256-bit\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMemory Bandwidth\u003c\/td\u003e\n\u003ctd\u003e273 GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eStorage\u003c\/td\u003e\n\u003ctd\u003e4 TB NVMe M.2 with self-encryption\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eUSB\u003c\/td\u003e\n\u003ctd\u003e4x USB Type-C\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eEthernet\u003c\/td\u003e\n\u003ctd\u003e1x RJ-45 connector, 10 GbE\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNIC\u003c\/td\u003e\n\u003ctd\u003eConnectX-7 NIC @ 200 Gbps (2x QSFP ports)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eWi-Fi\u003c\/td\u003e\n\u003ctd\u003eWi-Fi 7\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eBluetooth\u003c\/td\u003e\n\u003ctd\u003eBT 5.4\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eAudio Output\u003c\/td\u003e\n\u003ctd\u003eHDMI multichannel audio output\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDisplay Connectors\u003c\/td\u003e\n\u003ctd\u003e1x HDMI 2.1a, up to 3x DisplayPort over USB-C (DP Alt Mode)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNVENC | NVDEC\u003c\/td\u003e\n\u003ctd\u003e1x | 1x\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePower Supply\u003c\/td\u003e\n\u003ctd\u003e240 W (included)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eGB10 TDP\u003c\/td\u003e\n\u003ctd\u003e140 W\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eOS\u003c\/td\u003e\n\u003ctd\u003eNVIDIA DGX OS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eSystem Dimensions\u003c\/td\u003e\n\u003ctd\u003e150 mm L x 150 mm W x 50.5 mm H\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eSystem Weight\u003c\/td\u003e\n\u003ctd\u003e1.2 kg\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eOperating Temperature\u003c\/td\u003e\n\u003ctd\u003e5°C to 30°C\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":68107814633701,"sku":"940-54242-0000-000","price":720000.0,"currency_code":"INR","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0536\/4803\/1936\/files\/nvidia_dgx_spark_-2.png?v=1794471632","url":"https:\/\/golchhait.com\/products\/nvidia-dgx-spark-personal-ai-supercomputer-gb10-grace-blackwell-128gb-unified-memory-4tb-ssd","provider":"GOLCHHA COMPUTERS ","version":"1.0","type":"link"}