{"product_id":"nvidia-h200-gpu","title":"NVIDIA H200 NVL Graphic Card 141 GB Passive PCIe","description":"\u003ch2 style=\"text-align: center;\"\u003eNVIDIA H200 NVL Graphic Card \u003c\/h2\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cstrong\u003e\u003cspan style=\"color: rgb(115, 194, 34);\"\u003e900-21010-0040-000\u003c\/span\u003e\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eNVIDIA H200 NVL is ideal for lower-power, air-cooled enterprise rack designs that require flexible configurations, delivering acceleration for every AI and HPC workload regardless of size. With up to four GPUs connected by NVIDIA NVLink™ and a 1.5X memory increase, large language model (LLM) inference can be accelerated up to 1.7X and HPC applications achieve up to 1.3X more performance over the H100 NVL.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0014\/4313\/5560\/files\/h200nvl-ari.jpg?v=1765343797\" alt=\"\"\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003ch2 style=\"text-align: center;\"\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eNVIDIA H200 GPU\u003c\/span\u003e\u003c\/h2\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cspan style=\"color: rgb(115, 194, 34);\"\u003e\u003cstrong\u003eSupercharging AI and HPC workloads.\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cimg alt=\"\" src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0014\/4313\/5560\/files\/h200-kv-bb580_440-p_2x_c509abc6-b079-440a-ba94-85a6f42054c2.jpg?v=1765349204\"\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003ch2 style=\"text-align: center;\"\u003e\u003cspan style=\"color: rgb(115, 194, 34);\"\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eThe GPU for Generative AI and HPC\u003c\/span\u003e\u003cstrong\u003e\u003cbr\u003e\u003c\/strong\u003e\u003c\/span\u003e\u003c\/h2\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cspan style=\"color: rgb(0, 0, 0);\"\u003eThe NVIDIA H200 GPU supercharges generative AI and high-performance computing (HPC) workloads with game-changing performance and memory capabilities. As the first GPU with HBM3E, the H200’s larger and faster memory fuels the acceleration of generative AI and large language models (LLMs) while advancing scientific computing for HPC workloads.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003ch2 style=\"text-align: center;\"\u003eExperience Next-Level Performance\u003cbr\u003e\n\u003c\/h2\u003e\n\u003ctable style=\"width: 90%; margin: auto; height: 97.141px;\"\u003e\n\u003ctbody\u003e\n\u003ctr style=\"height: 97.141px;\"\u003e\n\u003ctd style=\"border: 0px; text-align: center; vertical-align: top; width: 33.3051%; height: 97.141px;\"\u003e\n\u003ch2\u003e\u003cspan style=\"color: rgb(115, 194, 34);\"\u003e\u003cspan class=\"leadPerf\"\u003e1.9X\u003c\/span\u003e Faster\u003c\/span\u003e\u003c\/h2\u003e\n\u003cp\u003e\u003cstrong\u003eLlama2 70B Inference\u003c\/strong\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd style=\"border: 0px; text-align: center; vertical-align: top; width: 33.0454%; height: 97.141px;\"\u003e\n\u003ch2\u003e\u003cspan style=\"color: rgb(115, 194, 34);\"\u003e\u003cspan class=\"leadPerf\"\u003e1.6X\u003c\/span\u003e Faster\u003c\/span\u003e\u003c\/h2\u003e\n\u003cp\u003e\u003cstrong\u003eGPT-3 175B Inference\u003c\/strong\u003e\u003c\/p\u003e\n\u003c\/td\u003e\n\u003ctd style=\"border: 0px; text-align: center; vertical-align: top; width: 32.8025%; height: 97.141px;\"\u003e\n\u003cdiv class=\"nv-container container responsivegrid aem-GridColumn aem-GridColumn--default--12\"\u003e\n\u003cdiv id=\"highlights\" class=\"p-t-75 p-b-75  lap-p-t-75 \n         lap-p-b-75  tab-p-t-45 tab-p-b-45\n          mob-p-t-45 mob-p-b-45  \n          \n          \n         d-top-align d-left-align \n         l-left-align l-top-align t-left-align \n         t-top-align m-top-align m-left-align \n             \n         d-content-align-top l-content-align-top t-content-align-top m-content-align-top\" data-cmp-is=\"nv-container\" data-cmp-breadcrumbcolor=\"none\" data-in-page-nav-item-index=\"2\"\u003e\n\u003cdiv class=\"general-container\"\u003e\n\u003cdiv class=\"aem-Grid aem-Grid--12 aem-Grid--default--12\"\u003e\n\u003cdiv class=\"nv-container container responsivegrid aem-GridColumn aem-GridColumn--default--12\"\u003e\n\u003cdiv id=\"container-3a785f44cc\" class=\"p-t-30 p-b-0  lap-p-t-30 \n         lap-p-b-0  tab-p-t-30 tab-p-b-0 \n          mob-p-t-30 mob-p-b-0  \n          \n          \n         d-top-align d-left-align \n         l-left-align l-top-align t-left-align \n         t-top-align m-top-align m-left-align \n             \n         d-content-align-top l-content-align-top t-content-align-top m-content-align-top\" data-cmp-is=\"nv-container\"\u003e\n\u003cdiv class=\"general-container nv-flexbox d-col-3 l-col-3 t-col-2 p-col-1 d-justify-center l-justify-center t-justify-center p-justify-center flex-align-stretch\"\u003e\n\u003cdiv class=\"nv-container container responsivegrid\"\u003e\n\u003cdiv id=\"container-df03b36c44\" class=\"p-t-0 p-b-0  lap-p-t-0 \n         lap-p-b-0  tab-p-t-30 tab-p-b-0\n          mob-p-t-30 mob-p-b-0  \n          \n          \n         d-top-align d-left-align \n         l-left-align l-top-align t-left-align \n         t-top-align m-top-align m-left-align \n             \n         d-content-align-top l-content-align-top t-content-align-top m-content-align-top\" data-cmp-is=\"nv-container\" data-cmp-breadcrumbcolor=\"none\"\u003e\n\u003cdiv class=\"general-container\"\u003e\n\u003cdiv class=\"aem-Grid aem-Grid--12 aem-Grid--default--12\"\u003e\n\u003cdiv class=\"nv-text text aem-GridColumn aem-GridColumn--default--12\"\u003e\n\u003cdiv id=\"nv-text-df620d9d5d\" class=\"general-container-text\"\u003e\n\u003cdiv class=\"text-center lap-text-center tab-text-center mob-text-center\"\u003e\n\u003cdiv class=\"description\"\u003e\n\u003ch2\u003e\u003cspan style=\"color: rgb(115, 194, 34);\"\u003e\u003cspan class=\"leadPerf\"\u003e110X\u003c\/span\u003e Faster\u003c\/span\u003e\u003c\/h2\u003e\n\u003cp\u003e\u003cstrong\u003eHigh-Performance Computing\u003c\/strong\u003e\u003cbr\u003e\u003c\/p\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003c\/div\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;\"\u003eHigher Performance With Larger, Faster Memory\u003cbr\u003e\n\u003c\/h2\u003e\n\u003cp style=\"text-align: center;\"\u003eBased on the NVIDIA Hopper™ architecture, the NVIDIA H200 is the first GPU to offer 141 gigabytes (GB) of HBM3e memory at 4.8 terabytes per second (TB\/s) —that’s nearly double the capacity of the NVIDIA H100 GPU with 1.4X more memory bandwidth. The H200’s larger and faster memory accelerates generative AI and LLMs, while advancing scientific computing for HPC workloads with better energy efficiency and lower total cost of ownership.\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003ch2 style=\"text-align: center;\"\u003eUnlock Insights With High-Performance LLM Inference\u003c\/h2\u003e\n\u003cp style=\"text-align: center;\"\u003eIn the ever-evolving landscape of AI, businesses rely on LLMs to address a diverse range of inference needs. An AI inference accelerator must deliver the highest throughput at the lowest TCO when deployed at scale for a massive user base.\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003eThe H200 boosts inference speed by up to 2X compared to H100 GPUs when handling LLMs like Llama2.\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003ca href=\"https:\/\/www.nvidia.com\/en-us\/deep-learning-ai\/solutions\/inference-platform\/?ncid=no-ncid\" rel=\"noopener\" target=\"_blank\"\u003eExplore NVIDIA’s AI Inference Platform \u0026gt;\u003c\/a\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0014\/4313\/5560\/files\/llm-inference-chart_1.svg?v=1765343362\" alt=\"\"\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cstrong\u003ePreliminary specifications. May be subject to change.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003eLlama2 13B: ISL 128, OSL 2K | Throughput | H100 SXM 1x GPU BS 64 | H200 SXM 1x GPU BS 128\u003cbr\u003eGPT-3 175B: ISL 80, OSL 200 | x8 H100 SXM GPUs BS 64 | x8 H200 SXM GPUs BS 128\u003cbr\u003eLlama2 70B: ISL 2K, OSL 128 | Throughput | H100 SXM 1x GPU BS 8 | H200 SXM 1x GPU BS 32.\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003ch2 style=\"text-align: center;\"\u003eSupercharge High-Performance Computing\u003c\/h2\u003e\n\u003cp style=\"text-align: center;\"\u003eMemory bandwidth is crucial for HPC applications as it enables faster data transfer, reducing complex processing bottlenecks. For memory-intensive HPC applications like simulations, scientific research, and artificial intelligence, the H200’s higher memory bandwidth ensures that data can be accessed and manipulated efficiently, leading up to 110X faster time to results compared to CPUs.\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003ca href=\"https:\/\/www.nvidia.com\/en-us\/high-performance-computing\/?ncid=no-ncid\" rel=\"noopener\" target=\"_blank\"\u003eLearn More About High-Performance Computing \u0026gt;\u003c\/a\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0014\/4313\/5560\/files\/high-performance-computing-chart.svg?v=1765343458\" alt=\"\"\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cstrong\u003ePreliminary specifications. May be subject to change.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003eHPC MILC- dataset NERSC Apex Medium | HGX H200 4-GPU | dual Sapphire Rapids 8480\u003cbr\u003eHPC Apps- CP2K: dataset H2O-32-RI-dRPA-96points | GROMACS: dataset STMV | ICON: dataset r2b5 | MILC: dataset NERSC Apex Medium | Chroma: dataset HMC Medium | Quantum Espresso: dataset AUSURF112 | 1x H100 SXM | 1x H200 SXM.\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003ch2 style=\"text-align: center;\"\u003eReduce Energy and TCO\u003c\/h2\u003e\n\u003cp style=\"text-align: center;\"\u003eWith the introduction of the H200, energy efficiency and TCO reach new levels. This cutting-edge technology offers unparalleled performance, all within the same power profile as the H100. AI factories and supercomputing systems that are not only faster but also more eco-friendly, deliver an economic edge that propels the AI and scientific community forward.\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003ca href=\"https:\/\/www.nvidia.com\/en-us\/data-center\/sustainable-computing\/?ncid=no-ncid\" rel=\"noopener\" target=\"_blank\"\u003eLearn More About Sustainable Computing \u0026gt;\u003c\/a\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0014\/4313\/5560\/files\/energy-tco-chart.svg?v=1765343557\" alt=\"\" style=\"font-size: 0.875rem;\"\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cstrong\u003ePreliminary specifications. May be subject to change.\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003eLlama2 70B: ISL 2K, OSL 128 | Throughput | H100 SXM 1x GPU BS 8 | H200 SXM 1x GPU BS 32\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003ch2 style=\"text-align: center;\"\u003eAccelerating AI Acceleration for Mainstream Enterprise Servers With H200 NVL\u003cbr\u003e\n\u003c\/h2\u003e\n\u003cp style=\"text-align: center;\"\u003eNVIDIA H200 NVL is ideal for lower-power, air-cooled enterprise rack designs that require flexible configurations, delivering acceleration for every AI and HPC workload regardless of size. With up to four GPUs connected by NVIDIA NVLink™ and a 1.5x memory increase, large language model (LLM) inference can be accelerated up to 1.7x, and HPC applications achieve up to 1.3x more performance over the H100 NVL.\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0014\/4313\/5560\/files\/h200nvl-ari.jpg?v=1765343797\" alt=\"\"\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003ch2 style=\"text-align: center;\"\u003eEnterprise-Ready: AI Software Streamlines Development and Deployment\u003c\/h2\u003e\n\u003cp style=\"text-align: center;\"\u003eNVIDIA H200 NVL comes with a five-year NVIDIA Enterprise subscription. This subscription includes NVIDIA AI Enterprise to simplify the way you build an enterprise AI-ready platform. H200 accelerates AI development and deployment for production-ready generative AI solutions, including computer vision, speech AI, retrieval augmented generation (RAG), and more. NVIDIA AI Enterprise includes NVIDIA NIM™, a set of easy-to-use microservices designed to speed up enterprise generative AI deployment. Together, deployments have enterprise-grade security, manageability, stability, and support. This results in performance-optimized AI solutions that deliver faster business value and actionable insights.\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003ca href=\"https:\/\/www.nvidia.com\/en-us\/data-center\/activate-license\/?ncid=no-ncid\" rel=\"noopener\" target=\"_blank\"\u003eActivate Your NVIDIA AI Enterprise License \u0026gt;\u003c\/a\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cimg src=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0014\/4313\/5560\/files\/ai-enterprise-kv-bm-af360-p_2x_52a142c2-70d5-4d47-8fd5-b1053843bf42.jpg?v=1765343884\" alt=\"\"\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003ch2 style=\"text-align: center;\"\u003eGraphics memory\u003c\/h2\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cspan style=\"color: rgb(115, 194, 34);\"\u003e\u003cstrong\u003eMemory size 141 GB┃Memory type HBM3e\u003c\/strong\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003eVRAM, these days primarily of GDDR type, is a synchronous memory, similar to standard RAM. However, in the case of graphic memory, memory chips with faster throughput and multiple data transfer rates are concerned. The result is a much faster buffering of data that the graphics card or coprocessor calculates and passes to the processor.\u003c\/p\u003e\n\u003cp style=\"text-align: center;\"\u003e \u003c\/p\u003e\n\u003ch2 style=\"text-align: center;\"\u003eSpecifications\u003c\/h2\u003e\n\u003cp style=\"text-align: center;\"\u003e\u003cstrong\u003eNVIDIA H200 GPU\u003c\/strong\u003e\u003cbr\u003e\u003c\/p\u003e\n\u003ctable style=\"border-collapse: collapse; width: 100%; height: 685.808px;\"\u003e\n\u003ctbody\u003e\n\u003ctr style=\"height: 19.5964px;\"\u003e\n\u003cth style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003e\u003cstrong\u003eSpecification\u003c\/strong\u003e\u003c\/th\u003e\n\u003cth style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003e\u003cstrong\u003e\u003cspan style=\"color: rgb(115, 194, 34);\"\u003eH200 SXM\u003c\/span\u003e\u003c\/strong\u003e\u003c\/th\u003e\n\u003cth style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003e\u003cstrong\u003e\u003cspan style=\"color: rgb(115, 194, 34);\"\u003eH200 NVL\u003c\/span\u003e\u003c\/strong\u003e\u003c\/th\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 39.1797px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1797px; text-align: center;\"\u003eFP64 Performance\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1797px; text-align: center;\"\u003e34 TFLOPS\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1797px; text-align: center;\"\u003e30 TFLOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5964px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003eFP64 Tensor Core\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003e67 TFLOPS\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003e60 TFLOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 39.1797px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1797px; text-align: center;\"\u003eFP32 Performance\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1797px; text-align: center;\"\u003e67 TFLOPS\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1797px; text-align: center;\"\u003e60 TFLOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5964px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003eTF32 Tensor Core\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003e989 TFLOPS\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003e835 TFLOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 39.1927px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1927px; text-align: center;\"\u003eBFLOAT16 Tensor Core\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1927px; text-align: center;\"\u003e1,979 TFLOPS\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1927px; text-align: center;\"\u003e1,671 TFLOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5964px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003eFP16 Tensor Core\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003e1,979 TFLOPS\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003e1,671 TFLOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5964px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003eFP8 Tensor Core\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003e3,958 TFLOPS\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003e3,341 TFLOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5964px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003eINT8 Tensor Core\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003e3,958 TFLOPS\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003e3,341 TFLOPS\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5964px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003eGPU Memory\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003e141 GB\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003e141 GB\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 39.1927px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1927px; text-align: center;\"\u003eGPU Memory Bandwidth\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1927px; text-align: center;\"\u003e4.8 TB\/s\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1927px; text-align: center;\"\u003e4.8 TB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 19.5964px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003eDecoders\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003e7 × NVDEC, 7 × JPEG\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 19.5964px; text-align: center;\"\u003e7 × NVDEC, 7 × JPEG\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 39.1927px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1927px; text-align: center;\"\u003eConfidential Computing\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1927px; text-align: center;\"\u003eSupported\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1927px; text-align: center;\"\u003eSupported\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 39.1797px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1797px; text-align: center;\"\u003eMax TDP\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1797px; text-align: center;\"\u003eUp to 700 W (configurable)\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1797px; text-align: center;\"\u003eUp to 600 W (configurable)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 39.1927px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1927px; text-align: center;\"\u003eMulti-Instance GPU (MIG)\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1927px; text-align: center;\"\u003eUp to 7 MIGs @ 18 GB each\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1927px; text-align: center;\"\u003eUp to 7 MIGs @ 16.5 GB each\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 39.1797px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1797px; text-align: center;\"\u003eForm Factor\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1797px; text-align: center;\"\u003eSXM\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1797px; text-align: center;\"\u003ePCIe, dual-slot air-cooled\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 78.3724px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 78.3724px; text-align: center;\"\u003eInterconnect\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 78.3724px; text-align: center;\"\u003eNVIDIA NVLink™: 900 GB\/s\u003cbr\u003ePCIe Gen5: 128 GB\/s\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 78.3724px; text-align: center;\"\u003e2- or 4-way NVLink bridge: 900 GB\/s per GPU\u003cbr\u003ePCIe Gen5: 128 GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 97.9818px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 97.9818px; text-align: center;\"\u003eServer Options\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 97.9818px; text-align: center;\"\u003eNVIDIA HGX™ H200 partner systems\u003cbr\u003eNVIDIA-Certified™ systems with 4 or 8 GPUs\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 97.9818px; text-align: center;\"\u003eNVIDIA MGX™ H200 NVL partner systems\u003cbr\u003eNVIDIA-Certified™ systems with up to 8 GPUs\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr style=\"height: 39.1927px;\"\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1927px; text-align: center;\"\u003eNVIDIA AI Enterprise\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1927px; text-align: center;\"\u003eAdd-on\u003c\/td\u003e\n\u003ctd style=\"border: 1px solid rgb(0, 0, 0); padding: 8px; height: 39.1927px; text-align: center;\"\u003eIncluded\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;\"\u003eResources\u003c\/h2\u003e\n\u003ctable style=\"border-collapse: collapse;\"\u003e\n\u003ctbody\u003e\n\u003ctr\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\/hpc-datasheet-sc23-h200-datasheet-3002446.pdf?v=1765347919\" target=\"_blank\"\u003e\u003cspan style=\"color: rgb(43, 0, 255);\"\u003e\u003cstrong\u003eDatasheet\u003c\/strong\u003e\u003c\/span\u003e\u003c\/a\u003e\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;\"\u003e\u003ca rel=\"noopener\" href=\"https:\/\/cdn.shopify.com\/s\/files\/1\/0014\/4313\/5560\/files\/hpc-datasheet-sc23-h200-datasheet-3002446.pdf?v=1765347919\" target=\"_blank\"\u003e\u003cspan style=\"color: rgb(43, 0, 255);\"\u003e\u003cstrong\u003eH200 NVL Product Brief \u003c\/strong\u003e\u003c\/span\u003e\u003c\/a\u003e\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;\"\u003e\u003ca rel=\"noopener\" href=\"https:\/\/developer.nvidia.com\/deep-learning-performance-training-inference?ncid=no-ncid\" target=\"_blank\"\u003e\u003cspan style=\"color: rgb(43, 0, 255);\"\u003e\u003cstrong\u003eData Center Product Performance\u003c\/strong\u003e\u003c\/span\u003e\u003c\/a\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":51148332663101,"sku":"H200","price":2949999.99,"currency_code":"INR","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0014\/4313\/5560\/files\/Gemini_Generated_Image_gxpdmygxpdmygxpd.png?v=1765349919","url":"https:\/\/thinkrobotics.com\/es\/products\/nvidia-h200-gpu","provider":"Atlantis Robotics","version":"1.0","type":"link"}