{"title":"Graphics Cards","description":"\u003cp\u003eProfessional and enterprise graphics cards provide dedicated GPU compute and visual output capabilities for workstations, rendering servers, and AI development environments. From high-performance workstation GPUs designed for CAD, 3D visualisation, and real-time rendering to compute-focused cards for machine learning development and data science workflows, the right graphics card can significantly accelerate creative and technical workloads. This collection covers a range of GPU options suited to desktop workstations and rack-mounted servers, spanning products from NVIDIA's professional and consumer GPU lineups.\u003c\/p\u003e","products":[{"product_id":"900-21001-0020-100-a100-80gb-pcie","title":"900-21001-0020-100 NVIDIA A100 80GB PCIE - Graphics Card - New Retail","description":"\u003cp class=\"font-claude-response-body break-words whitespace-normal\"\u003eThe NVIDIA® A100 80GB PCIe card delivers unprecedented acceleration to power the world's highest-performing elastic data centres for AI, data analytics, and high-performance computing (HPC) applications. NVIDIA A100 Tensor Core technology supports a broad range of math precisions, providing a single accelerator for every compute workload. The NVIDIA A100 80GB PCIe supports double precision (FP64), single precision (FP32), half precision (FP16), and integer (INT8) compute tasks.\u003c\/p\u003e\n\u003cp class=\"font-claude-response-body break-words whitespace-normal\"\u003eThe NVIDIA A100 80GB card is a dual-slot 10.5-inch PCI Express Gen4 card based on the NVIDIA Ampere GA100 graphics processing unit (GPU). It uses a passive heat sink for cooling, which requires system airflow to properly operate the card within its thermal limits. The NVIDIA A100 80GB PCIe operates unconstrained up to its maximum thermal design power (TDP) level of 300W to accelerate applications that require the fastest computational speed and highest data throughput. The latest generation A100 80GB PCIe doubles GPU memory and debuts the world's highest PCIe card memory bandwidth at up to 1.94 terabytes per second (TB\/s), speeding time to solution for the largest models and most massive datasets.\u003c\/p\u003e\n\u003cp class=\"font-claude-response-body break-words whitespace-normal\"\u003eThe NVIDIA A100 80GB PCIe card features Multi-Instance GPU (MIG) capability, which can be partitioned into as many as seven isolated GPU instances, providing a unified platform that enables elastic data centres to dynamically adjust to shifting workload demands. When using MIG to partition an A100 GPU into up to seven smaller instances, the A100 can readily handle different-sized acceleration needs, from the smallest job to the biggest multi-node workload. A100 80GB versatility means IT managers can maximise the utility of every GPU in their data centre.\u003c\/p\u003e\n\u003cp class=\"font-claude-response-body break-words whitespace-normal\"\u003eNVIDIA A100 80GB PCIe cards use three NVIDIA® NVLink® bridges that allow multiple A100 80GB PCIe cards to be connected together to deliver 600 GB\/s bandwidth — 10x the bandwidth of PCIe Gen4 — in order to maximise application throughput with larger workloads.\u003c\/p\u003e\n\u003c!----\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48724805091656,"sku":"900-21001-0020-100","price":19420.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-21001-0020-100-a100-80gb-pcie.jpg?v=1790505168"},{"product_id":"900-21010-0000-000-h100-80gb-pcie","title":"900-21010-0000-000 NVIDIA H100 80GB PCIE - Graphics Card - New Retail","description":"\u003cp\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eThe NVIDIA® H100 Tensor Core GPU delivers unprecedented acceleration to power the world’s highest-performing elastic data centres for AI, data analytics, and high-performance \u003cbr\u003ecomputing (HPC) applications. NVIDIA H100 Tensor Core technology supports a broad range of math precisions, providing a single accelerator for every compute workload. The NVIDIA H100 PCIe supports double precision (FP64), single-precision (FP32), half precision (FP16), and integer (INT8) compute tasks.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eNVIDIA H100 Tensor Core graphics processing units (GPUs) for mainstream servers comes \u003cbr\u003ewith an NVIDIA AI Enterprise five-year software subscription and includes enterprise support, \u003cbr\u003esimplifying AI adoption with the highest performance. This ensures organizations have access \u003cbr\u003eto the AI frameworks and tools needed to build H100 accelerated AI workflows such as \u003cbr\u003econversational AI, recommendation engines, vision AI, and more. \u003cbr\u003eActivate NVIDIA AI Enterprise license for H100 at: https:\/\/www.nvidia.com\/activate-h100\/\u003cbr\u003eThe NVIDIA H100 card is a dual-slot 10.5 inch PCI Express Gen5 card based on the NVIDIA \u003cbr\u003eHopper™ architecture. It uses a passive heat sink for cooling, which requires system airflow to \u003cbr\u003eoperate the card properly within its thermal limits. The NVIDIA H100 PCIe operates \u003cbr\u003eunconstrained up to its maximum thermal design power (TDP) level of 350 W to accelerate \u003cbr\u003eapplications that require the fastest computational speed and highest data throughput. The \u003cbr\u003eNVIDIA H100 PCIe debuts the world’s highest PCIe card memory bandwidth greater than 2,000 gigabytes per second (GBps). This speeds time to solution for the largest models and most massive data sets. \u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003e\u003cbr\u003eThe NVIDIA H100 PCIe card features Multi-Instance GPU (MIG) capability. This can be used to \u003cbr\u003epartition the GPU into as many as seven hardware-isolated GPU instances, providing a unified \u003cbr\u003eplatform that enables elastic data centers to adjust dynamically to shifting workload demands. \u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003e\u003cbr\u003eAs well as one can allocate the right size of resources from the smallest to biggest multi-GPU \u003cbr\u003ejobs. NVIDIA H100 versatility means that IT managers can maximize the utility of every GPU in \u003cbr\u003etheir data centre.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eNVIDIA H100 PCIe cards use three NVIDIA® NVLink® bridges. They are the same as the bridges used with NVIDIA A100 PCIe cards. This allows two NVIDIA H100 PCIe cards to be connected to deliver 900 GB\/s bidirectional bandwidth or 5x the bandwidth of PCIe Gen5, to maximize application performance for large workloads. \u003c\/span\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003e\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eThe NVIDIA H100 Tensor Core GPU delivers exceptional performance, scalability,\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eand security for every workload. With NVIDIA® NVLink® Switch System, up to 256\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eH100 GPUs can be connected to accelerate exascale workloads, while the dedicated\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eTransformer Engine supports trillion-parameter language models. H100 uses\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003ebreakthrough innovations in the NVIDIA Hopper\u003c\/span\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003e™\u003c\/span\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003e \u003c\/span\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003earchitecture to deliver industry-\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eleading conversational AI, speeding up large language models by 30X over the\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eprevious generation.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cbr role=\"presentation\"\u003e\u003cstrong\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eReady for Enterprise AI?\u003c\/span\u003e\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eNVIDIA H100 GPUs for mainstream servers come with a five-year software\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003esubscription, including enterprise support, to the NVIDIA AI Enterprise software\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003esuite, simplifying AI adoption with the highest performance. This ensures\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eorganizations have access to the AI frameworks and tools they need to build H100-\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eaccelerated AI workflows such as AI chatbots, recommendation engines, vision AI,\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eand more.\u003c\/span\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003e \u003c\/span\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eAccess the NVIDIA AI Enterprise software subscription\u003c\/span\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003e \u003c\/span\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eand related\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003esupport benefits for the NVIDIA H100.\u003c\/span\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cbr role=\"presentation\"\u003e\u003cstrong\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eSecurely Accelerate Workloads From Enterprise to Exascale\u003c\/span\u003e\u003c\/strong\u003e\u003c\/p\u003e\n\u003cp\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eNVIDIA H100 GPUs feature fourth-generation Tensor Cores and the Transformer\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eEngine with FP8 precision, further extending NVIDIA’s market-leading AI leadership\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003ewith up to 9X faster training and an incredible 30X inference speedup on large\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003elanguage models. For high-performance computing (HPC) applications, H100\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003etriples the floating-point operations per second (FLOPS) of FP64 and adds\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003edynamic programming (DPX) instructions to deliver up to 7X higher performance.\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eWith second-generation Multi-Instance GPU (MIG), built-in NVIDIA confidential\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003ecomputing, and NVIDIA NVLink Switch System, H100 securely accelerates all\u003c\/span\u003e\u003cbr role=\"presentation\"\u003e\u003cspan role=\"presentation\" dir=\"ltr\"\u003eworkloads for every data center from enterprise to exascale.\u003c\/span\u003e\u003c\/p\u003e\n\u003c!----\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48725747597640,"sku":"900-21010-0000-000","price":29425.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/12.png?v=1787237622"},{"product_id":"nvh100nvltcgpu-kit-nvidia-h100-lvl-80gb-graphics-card-pcie","title":"NVH100NVLTCGPU-KIT Nvidia H100 LVL 80GB Graphics Card - PCIe","description":"\u003cp\u003eNVIDIA H100 GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 80GB HBM3\u003c\/li\u003e\n\u003cli\u003eBandwidth: ~2,000GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Hopper architecture\u003c\/li\u003e\n\u003cli\u003ePerformance: up to 1,513 TFLOPS FP8 \/ 757 TFLOPS FP16 (with sparsity)\u003c\/li\u003e\n\u003cli\u003eTDP: 350W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe, dual-slot, NVLink bridge-capable\u003c\/li\u003e\n\u003cli\u003eIdeal for: large-scale AI training and inference, HPC\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48725748515144,"sku":null,"price":29425.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/image-removebg-preview-2024-09-13T093312.816_bdfa1ffd-b0fe-4215-8359-7e7828ebdc50.png?v=1726216489"},{"product_id":"900-2g133-0000-100-nvidia-a40-passive-pcie-48gb","title":"900-2G133-0000-100 NVIDIA A40 PASSIVE PCIE 48GB - NEW","description":"","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48725786427720,"sku":null,"price":5500.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-2g133-0000-100-nvidia-a40-passive-pcie-48gb.jpg?v=1790505167"},{"product_id":"900-21010-0020-000-h100-94gb-nvlink","title":"900-21010-0020-000 NVIDIA H100 NVL 94GB PCIe Accelerator - NEW - 3 YEAR WARRANTY","description":"\u003cp\u003eThe NVIDIA® H100 NVL Tensor Core GPU is the most optimized platform for LLM \u003cbr\u003eInferences with its high compute density, high memory bandwidth, high energy \u003cbr\u003eefficiency, and unique NVLink architecture. It also delivers unprecedented acceleration \u003cbr\u003eto power the world’s highest-performing elastic data centers for AI, data analytics, and \u003cbr\u003ehigh-performance computing (HPC) applications. NVIDIA H100 NVL Tensor Core \u003cbr\u003etechnology supports a broad range of math precisions, providing a single accelerator for \u003cbr\u003eevery compute workload. The NVIDIA H100 NVL supports double precision (FP64), singleprecision (FP32), half precision (FP16), 8-bit floating point (FP8), and integer (INT8) \u003cbr\u003ecompute tasks.\u003c\/p\u003e\n\u003cp\u003e\u003cbr\u003eThe NVIDIA H100 NVL card is a dual-slot 10.5 inch PCI Express Gen5 card based on the \u003cbr\u003eNVIDIA Hopper™ architecture. It uses a passive heat sink for cooling, which requires \u003cbr\u003esystem airflow to operate the card properly within its thermal limits. The NVIDIA H100 \u003cbr\u003eNVL operates unconstrained up to its maximum thermal design power (TDP) level of 400 \u003cbr\u003eW to accelerate applications that require the fastest computational speed and highest \u003cbr\u003edata throughput. The NVIDIA H100 NVL debuts the world’s highest PCIe card memory \u003cbr\u003ebandwidth of nearly 4,000 gigabytes per second (GBps). This speeds time to solution for \u003cbr\u003ethe largest models and most massive data sets.\u003c\/p\u003e\n\u003cp\u003e\u003cbr\u003eThe NVIDIA H100 NVL card features Multi-Instance GPU (MIG) capability. This can be \u003cbr\u003eused to partition the GPU into as many as seven hardware isolated GPU instances, \u003cbr\u003eproviding a unified platform that enables elastic data centers to adjust dynamically to \u003cbr\u003eshifting workload demands. As well as it can allocate the right size of resources from the \u003cbr\u003esmallest to biggest multi-GPU jobs. NVIDIA H100 NVL versatility means that IT managers \u003cbr\u003ecan maximize the utility of every graphics processing unit (GPU) in their data center.\u003cbr\u003eNVIDIA H100 NVL cards use three NVIDIA® NVLink® bridges. They are the same as the \u003cbr\u003eone used with NVIDIA H100 PCIe cards. This allows two NVIDIA H100 PCIe cards to be \u003cbr\u003econnected to deliver 600 GB\/s bidirectional bandwidth or 10x the bandwidth of PCIe \u003cbr\u003eGen4, to maximize application performance for large workloads\u003c\/p\u003e\n\u003c!----\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48725787705672,"sku":"900-21010-0020-000","price":23440.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/image-removebg-preview-2024-09-13T093312.816_3b148ee0-9234-4f34-a435-f289ac2180bd.png?v=1726216477"},{"product_id":"900-2g133-0020-100-nvidia-a10-24gb-graphics-card-pcie","title":"900-2G133-0020-100 Nvidia A10 24GB Graphics Card - PCIe","description":"\u003cp\u003eNVIDIA A10 24GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 24GB GDDR6\u003c\/li\u003e\n\u003cli\u003eBandwidth: 600GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ampere architecture\u003c\/li\u003e\n\u003cli\u003ePerformance: 31.2 TFLOPS FP32, up to 125 TFLOPS TF32 Tensor (with sparsity)\u003c\/li\u003e\n\u003cli\u003eTDP: 150W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe Gen4, 1-slot FHFL\u003c\/li\u003e\n\u003cli\u003eIdeal for: mixed AI inference, graphics and virtual workstation workloads\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48725789049160,"sku":null,"price":3500.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/image-removebg-preview-2024-09-13T102220.680.png?v=1726219358"},{"product_id":"900-21004-0030-000-a100x-80gb","title":"900-21004-0030-000 NVIDIA A100X 80GB","description":"\u003cp\u003eNVIDIA A100X GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 80GB HBM2e\u003c\/li\u003e\n\u003cli\u003eBandwidth: ~1,935GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: A100 GPU with integrated ConnectX SmartNIC\u003c\/li\u003e\n\u003cli\u003ePerformance: A100-class compute plus onboard networking\u003c\/li\u003e\n\u003cli\u003eTDP: 300W class\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe converged card\u003c\/li\u003e\n\u003cli\u003eIdeal for: GPU + high-speed networking in a single card for HGX\/DGX systems\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726088712520,"sku":null,"price":30000.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/EXX-IMG-7953863.webp?v=1720148131"},{"product_id":"900-5g178-2550-000-p1000-retail-pack","title":"900-5G178-2550-000 NVIDIA P1000 (retail pack)","description":"\u003cp\u003eNVIDIA Quadro P1000 4GB GPU (new, retail-packaged).\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 4GB GDDR5\u003c\/li\u003e\n\u003cli\u003eBandwidth: ~82GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Pascal architecture, 640 CUDA cores\u003c\/li\u003e\n\u003cli\u003ePerformance: entry-level workstation graphics\u003c\/li\u003e\n\u003cli\u003eTDP: 47W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe, low-profile, single-slot\u003c\/li\u003e\n\u003cli\u003eIdeal for: compact CAD, design and multi-display workstation use\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726089367880,"sku":null,"price":1000.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-5g178-2550-000-p1000-retail-pack.jpg?v=1790505167"},{"product_id":"900-5g212-2240-000-p620-bulk-pack","title":"900-5G212-2240-000 NVIDIA P620 (bulk pack)","description":"","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726089924936,"sku":null,"price":5000.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/10000880_10004606_400.jpg?v=1724947926"},{"product_id":"900-2g500-0010-000-tesla-v100-32g","title":"900-2G500-0010-000 NVIDIA Tesla V100 32G - NEW","description":"\u003cp\u003eNVIDIA Tesla V100 32GB GPU (new).\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 32GB HBM2\u003c\/li\u003e\n\u003cli\u003eBandwidth: 900GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: 5,120 CUDA cores, 640 Tensor cores (Volta)\u003c\/li\u003e\n\u003cli\u003ePerformance: 15.7 TFLOPS FP32, up to 125 TFLOPS Tensor\u003c\/li\u003e\n\u003cli\u003eTDP: 300W (SXM2) \/ 250W (PCIe)\u003c\/li\u003e\n\u003cli\u003eForm factor: SXM2 or PCIe, NVLink-capable (SXM2, 300GB\/s)\u003c\/li\u003e\n\u003cli\u003eIdeal for: HPC and deep learning training needing larger per-GPU memory\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726090940744,"sku":null,"price":5680.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/image-removebg-preview-2024-09-13T095240.792.png?v=1726217585"},{"product_id":"900-2g179-0020-100-a2-lp","title":"900-2G179-0020-100 NVIDIA A2 (LP)","description":"\u003cp\u003eNVIDIA A2 16GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 16GB GDDR6\u003c\/li\u003e\n\u003cli\u003eBandwidth: 200GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ampere architecture, 3rd-gen Tensor Cores\u003c\/li\u003e\n\u003cli\u003ePerformance: 4.5 TFLOPS FP32\u003c\/li\u003e\n\u003cli\u003eTDP: 40-60W (configurable)\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe Gen4 x8, 1-slot low-profile\u003c\/li\u003e\n\u003cli\u003eIdeal for: entry-level, low-power edge AI inference\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726091497800,"sku":null,"price":1515.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/image-removebg-preview-2024-09-13T101503.522.png?v=1726218960"},{"product_id":"900-2g179-0020-101-a2-atx","title":"900-2G179-0020-101 NVIDIA A2 (Atx)","description":"\u003cp\u003eNVIDIA A2 16GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 16GB GDDR6\u003c\/li\u003e\n\u003cli\u003eBandwidth: 200GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ampere architecture, 3rd-gen Tensor Cores\u003c\/li\u003e\n\u003cli\u003ePerformance: 4.5 TFLOPS FP32\u003c\/li\u003e\n\u003cli\u003eTDP: 40-60W (configurable)\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe Gen4 x8, 1-slot low-profile\u003c\/li\u003e\n\u003cli\u003eIdeal for: entry-level, low-power edge AI inference\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726092087624,"sku":null,"price":1325.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/image-removebg-preview-2024-09-13T101503.522.png?v=1726218960"},{"product_id":"900-2g133-0020-000-a10-24gb-pcie","title":"900-2G133-0020-000 NVIDIA A10 24GB PCIE -","description":"","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726092644680,"sku":null,"price":3400.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/253c93c2-cd52-4662-8f53-31227b49a50b.jpg?v=1724947925"},{"product_id":"900-2g171-0000-000-a16-64gb","title":"900-2G171-0000-000 NVIDIA A16 64GB","description":"\u003cp\u003eNVIDIA A16 64GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 64GB GDDR6 (4x16GB, one per onboard GPU)\u003c\/li\u003e\n\u003cli\u003eBandwidth: 4x Ampere GPUs on a single board\u003c\/li\u003e\n\u003cli\u003eCompute: four independent Ampere GPUs\u003c\/li\u003e\n\u003cli\u003ePerformance: high VDI user density via NVIDIA vGPU\u003c\/li\u003e\n\u003cli\u003eTDP: ~250W (card)\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe Gen4, dual-slot FHFL\u003c\/li\u003e\n\u003cli\u003eIdeal for: high-density virtual desktop infrastructure (VDI)\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726093267272,"sku":null,"price":3600.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-2g171-0000-000-a16-64gb.jpg?v=1790505166"},{"product_id":"900-21001-0040-100-a30-24gb","title":"900-21001-0040-100 NVIDIA A30 24GB","description":"\u003cp\u003eNVIDIA A30 24GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 24GB HBM2\u003c\/li\u003e\n\u003cli\u003eBandwidth: 933GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ampere architecture, Multi-Instance GPU (MIG) support\u003c\/li\u003e\n\u003cli\u003ePerformance: 10.3 TFLOPS FP32, up to 165 TFLOPS TF32 Tensor (with sparsity)\u003c\/li\u003e\n\u003cli\u003eTDP: 165W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe Gen4, dual-slot FHFL, NVLink-bridge capable\u003c\/li\u003e\n\u003cli\u003eIdeal for: mainstream AI inference\/training and HPC\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726093824328,"sku":null,"price":4800.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/253c93c2-cd52-4662-8f53-31227b49a50b.jpg?v=1724947925"},{"product_id":"900-2g133-0000-100-a40-48gb","title":"900-2G133-0000-100 NVIDIA A40 48GB","description":"","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726094250312,"sku":null,"price":5500.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-2g133-0000-100-a40-48gb.jpg?v=1790505170"},{"product_id":"900-21001-0000-000-a100-40gb","title":"900-21001-0000-000 NVIDIA A100 Ampere 40GB Graphics Card","description":"\u003ch1\u003e900-21001-0000-000 NVIDIA A100 Ampere 40GB Graphics Card\u003c\/h1\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003cdiv\u003eCUDA Cores - 6912\u003c\/div\u003e\n\u003cdiv\u003e\u003cbr\u003e\u003c\/div\u003e\n\u003cdiv\u003eTensor Cores - 432 (3RD GEN)\u003c\/div\u003e\n\u003cdiv\u003e\u003cbr\u003e\u003c\/div\u003e\n\u003cdiv\u003eGPU Memory - 40GB\u003c\/div\u003e\n\u003cdiv\u003e\u003cbr\u003e\u003c\/div\u003e\n\u003cdiv\u003eMemory Interface - \u003cspan\u003eHBM2\u003c\/span\u003e\n\u003c\/div\u003e\n\u003cdiv\u003e\u003cbr\u003e\u003c\/div\u003e\n\u003cdiv\u003eMemory Bandwidth - \u003cspan\u003e1.6TB\/S\u003c\/span\u003e\n\u003c\/div\u003e\n\u003cdiv\u003e\u003cbr\u003e\u003c\/div\u003e\n\u003cdiv\u003eMaximum Power Consumption - 250 W\u003c\/div\u003e\n\u003cp\u003e \u003c\/p\u003e\n\u003c!----\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726095397192,"sku":"900-21001-0000-000","price":15000.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/12.png?v=1787237622"},{"product_id":"900-5g192-2500-000-a2000-6g","title":"900-5G192-2500-000 NVIDIA A2000 6G","description":"\u003cp\u003eNVIDIA Quadro RTX A2000 6GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 6GB GDDR6 with ECC\u003c\/li\u003e\n\u003cli\u003eBandwidth: ~288GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ampere architecture, 3,328 CUDA cores\u003c\/li\u003e\n\u003cli\u003ePerformance: entry professional rendering and compute\u003c\/li\u003e\n\u003cli\u003eTDP: 70W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe 4.0, single-slot low-profile\u003c\/li\u003e\n\u003cli\u003eIdeal for: compact professional design workstation workloads\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726095724872,"sku":null,"price":1000.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/EXX-IMG-7627318.webp?v=1720147246"},{"product_id":"900-5g192-2551-000-a2000-12g","title":"900-5G192-2551-000 NVIDIA Quadro RTX A2000 12GB Professional Graphic Card - NEW","description":"\u003cp\u003eNVIDIA Quadro RTX A2000 12GB GPU (new).\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 12GB GDDR6\u003c\/li\u003e\n\u003cli\u003eBandwidth: ~288GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ampere architecture, 3,328 CUDA cores\u003c\/li\u003e\n\u003cli\u003ePerformance: entry professional rendering and compute\u003c\/li\u003e\n\u003cli\u003eTDP: 70W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe 4.0, single-slot low-profile\u003c\/li\u003e\n\u003cli\u003eIdeal for: compact professional design workstation workloads\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726096019784,"sku":"900-5G192-2551-000","price":650.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-5g192-2551-000-a2000-12g.jpg?v=1790505169"},{"product_id":"tcsl20pcie-pb-l20-48gb","title":"TCSL20PCIE-PB L20 48GB","description":"\u003cp\u003eNVIDIA L20 GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 48GB GDDR6 with ECC\u003c\/li\u003e\n\u003cli\u003eBandwidth: 864GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ada Lovelace architecture, 11,776 CUDA cores, 368 Tensor cores, 92 RT cores\u003c\/li\u003e\n\u003cli\u003ePerformance: 59.8 TFLOPS FP32, up to 239 TOPS INT8\/FP8 Tensor\u003c\/li\u003e\n\u003cli\u003eTDP: 275W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe Gen4 x16, dual-slot FHFL\u003c\/li\u003e\n\u003cli\u003eIdeal for: AI inference at data center scale\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726096183624,"sku":null,"price":4500.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-tcsl20pcie-pb-l20-48gb.jpg?v=1790505162"},{"product_id":"900-2g193-0000-000-l4-24gb-bulk-pack","title":"900-2G193-0000-000 NVIDIA L4 24GB (bulk pack)","description":"\u003cp\u003eNVIDIA L4 24GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 24GB GDDR6\u003c\/li\u003e\n\u003cli\u003eBandwidth: 300GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ada Lovelace architecture\u003c\/li\u003e\n\u003cli\u003ePerformance: 30.3 TFLOPS FP32, up to 242 TFLOPS FP16 Tensor (with sparsity)\u003c\/li\u003e\n\u003cli\u003eTDP: 72W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe Gen4, 1-slot low-profile\u003c\/li\u003e\n\u003cli\u003eIdeal for: AI inference, video and graphics at data center to edge scale\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726096413000,"sku":null,"price":2850.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-2g193-0000-000-l4-24gb-bulk-pack.jpg?v=1790505166"},{"product_id":"900-2g133-0010-000-l40-48gb","title":"900-2G133-0010-000 NVIDIA L40 48GB - New","description":"\u003cp\u003eNVIDIA L40 48GB GPU (new).\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 48GB GDDR6 with ECC\u003c\/li\u003e\n\u003cli\u003eBandwidth: 864GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: 18,176 CUDA cores, 568 Tensor cores, 142 RT cores\u003c\/li\u003e\n\u003cli\u003ePerformance: 90.5 TFLOPS FP32, 209 TFLOPS RT\u003c\/li\u003e\n\u003cli\u003eTDP: 300W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe, dual-slot, passively cooled\u003c\/li\u003e\n\u003cli\u003eIdeal for: rendering, virtual workstations and AI training in the data center\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726096609608,"sku":"900-2G133-0010-000","price":7590.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-2g133-0010-000-l40-48gb.jpg?v=1790505165"},{"product_id":"900-2g133-0080-000-l40s-48gb","title":"900-2G133-0080-000 NVIDIA L40S 48GB","description":"\u003cp\u003eNVIDIA L40S 48GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 48GB GDDR6 with ECC\u003c\/li\u003e\n\u003cli\u003eBandwidth: 864GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: 18,176 CUDA cores, 568 Tensor cores, 142 RT cores\u003c\/li\u003e\n\u003cli\u003ePerformance: 91.6 TFLOPS FP32, up to 1,466 TFLOPS FP8 Tensor (with sparsity)\u003c\/li\u003e\n\u003cli\u003eTDP: 350W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe, dual-slot, passively cooled\u003c\/li\u003e\n\u003cli\u003eIdeal for: universal workload GPU for generative AI training\/inference and graphics\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726096773448,"sku":null,"price":9935.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-2g133-0080-000-l40s-48gb.jpg?v=1790505168"},{"product_id":"900-2g183-6300-t00-t4-bulk-pack","title":"900-2G183-6300-T00 NVIDIA T4 (bulk pack)","description":"\u003cp\u003eNVIDIA T4 16GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 16GB GDDR6\u003c\/li\u003e\n\u003cli\u003eBandwidth: 320GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: 2,560 CUDA cores, 320 Turing Tensor Cores\u003c\/li\u003e\n\u003cli\u003ePerformance: 8.1 TFLOPS FP32, 65 TFLOPS FP16\u003c\/li\u003e\n\u003cli\u003eTDP: 70W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe, low-profile, single-slot\u003c\/li\u003e\n\u003cli\u003eIdeal for: AI inference, video transcoding and VDI at scale\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726097428808,"sku":null,"price":2000.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/se_900-2g183-6300-t00.jpg?v=1724947924"},{"product_id":"900-5g192-2240-000-rtx-2000ada","title":"900-5G192-2240-000 NVIDIA RTX 2000ADA","description":"\u003cp\u003eNVIDIA RTX 2000 Ada Generation 16GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 16GB GDDR6 with ECC\u003c\/li\u003e\n\u003cli\u003eBandwidth: ~224GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ada Lovelace architecture, 2,816 CUDA cores\u003c\/li\u003e\n\u003cli\u003ePerformance: entry professional rendering and AI-accelerated design\u003c\/li\u003e\n\u003cli\u003eTDP: 70W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe 4.0, single-slot low-profile\u003c\/li\u003e\n\u003cli\u003eIdeal for: compact professional design and AI workstation workloads\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726097494344,"sku":null,"price":650.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/12.png?v=1787237622"},{"product_id":"900-5g192-2541-000-rtx-2000ada","title":"900-5G192-2541-000 NVIDIA RTX 2000ADA","description":"\u003cp\u003eNVIDIA RTX 2000 Ada Generation 16GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 16GB GDDR6 with ECC\u003c\/li\u003e\n\u003cli\u003eBandwidth: ~224GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ada Lovelace architecture, 2,816 CUDA cores\u003c\/li\u003e\n\u003cli\u003ePerformance: entry professional rendering and AI-accelerated design\u003c\/li\u003e\n\u003cli\u003eTDP: 70W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe 4.0, single-slot low-profile\u003c\/li\u003e\n\u003cli\u003eIdeal for: compact professional design and AI workstation workloads\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726097527112,"sku":null,"price":850.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-5g192-2541-000-rtx-2000ada.jpg?v=1790505156"},{"product_id":"900-5g160-2250-000-rtx-4000","title":"900-5G160-2250-000 NVIDIA RTX 4000","description":"\u003cp\u003eNVIDIA Quadro RTX 4000 8GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 8GB GDDR6\u003c\/li\u003e\n\u003cli\u003eBandwidth: ~416GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Turing architecture, 2,304 CUDA cores\u003c\/li\u003e\n\u003cli\u003ePerformance: entry-to-mid professional rendering and ray tracing\u003c\/li\u003e\n\u003cli\u003eTDP: 160W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe 3.0, single-slot\u003c\/li\u003e\n\u003cli\u003eIdeal for: professional CAD, design and visualization workstation workloads\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726097625416,"sku":null,"price":1750.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/12.png?v=1787237622"},{"product_id":"900-5g190-2500-000-rtx-a4000-16gb-retail-pack","title":"900-5G190-2500-000 NVIDIA RTX A4000 16GB (retail pack)","description":"\u003cp\u003eNVIDIA RTX A4000 16GB GPU (new, retail-packaged).\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 16GB GDDR6\u003c\/li\u003e\n\u003cli\u003eBandwidth: 448GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: 6,144 CUDA cores\u003c\/li\u003e\n\u003cli\u003ePerformance: Ampere workstation-class rendering and compute\u003c\/li\u003e\n\u003cli\u003eTDP: 140W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe 4.0 x16, single-slot\u003c\/li\u003e\n\u003cli\u003eIdeal for: professional design, rendering and AI workstation workloads\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726097690952,"sku":null,"price":1050.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/EXX-IMG-7627318.webp?v=1720147246"},{"product_id":"900-5g132-2550-000-rtx-a4500","title":"900-5G132-2550-000 NVIDIA RTX A4500 20GB - New","description":"\u003cp\u003eNVIDIA RTX A4500 20GB GPU (new).\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 20GB GDDR6\u003c\/li\u003e\n\u003cli\u003eBandwidth: ~640GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: 7,168 CUDA cores\u003c\/li\u003e\n\u003cli\u003ePerformance: Ampere workstation-class rendering and compute\u003c\/li\u003e\n\u003cli\u003eTDP: 200W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe 4.0 x16, dual-slot\u003c\/li\u003e\n\u003cli\u003eIdeal for: professional 3D design, rendering and AI workstation workloads\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726097854792,"sku":null,"price":1550.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-5g132-2550-000-rtx-a4500.jpg?v=1790505166"},{"product_id":"900-5g132-2560-000-rtx-4500-ada-retail-pack","title":"900-5G132-2560-000 NVIDIA RTX 4500 ADA (retail pack)","description":"\u003cp\u003eNVIDIA RTX 4500 Ada Generation 24GB GPU (new, retail-packaged).\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 24GB GDDR6\u003c\/li\u003e\n\u003cli\u003eBandwidth: ~432GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ada Lovelace architecture, ~7,680 CUDA cores\u003c\/li\u003e\n\u003cli\u003ePerformance: professional rendering and AI-accelerated design\u003c\/li\u003e\n\u003cli\u003eTDP: 210W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe 4.0, dual-slot\u003c\/li\u003e\n\u003cli\u003eIdeal for: professional 3D design, rendering and AI workstation workloads\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726097953096,"sku":null,"price":2600.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-5g132-2560-000-rtx-4500-ada-retail-pack.jpg?v=1790505165"},{"product_id":"900-5g132-2560-000-rtx-4500ada","title":"900-5G132-2560-000 NVIDIA RTX 4500 Ada","description":"\u003cp\u003eNVIDIA RTX 4500 Ada Generation 24GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 24GB GDDR6\u003c\/li\u003e\n\u003cli\u003eBandwidth: ~432GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ada Lovelace architecture, ~7,680 CUDA cores\u003c\/li\u003e\n\u003cli\u003ePerformance: professional rendering and AI-accelerated design\u003c\/li\u003e\n\u003cli\u003eTDP: 210W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe 4.0, dual-slot\u003c\/li\u003e\n\u003cli\u003eIdeal for: professional 3D design, rendering and AI workstation workloads\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726098182472,"sku":null,"price":2600.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/12.png?v=1787237622"},{"product_id":"900-5g132-2200-000-rtx-a5000-bulk-pack","title":"900-5G132-2200-000 NVIDIA RTX A5000 (bulk pack)","description":"","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726098280776,"sku":null,"price":2300.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-5g132-2200-000-rtx-a5000-bulk-pack.jpg?v=1790505167"},{"product_id":"900-5g132-2500-000-rtx-a5000-retail-pack","title":"900-5G132-2500-000 NVIDIA RTX A5000 (retail pack)","description":"","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726098313544,"sku":null,"price":2400.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/unnamed_2efc9465-f1f1-4da3-9a67-fd4dc2c64e03.jpg?v=1720146930"},{"product_id":"900-5g132-2240-000-rtx-5000-ada-bulk-pack","title":"900-5G132-2240-000 NVIDIA RTX 5000 ADA (bulk pack)","description":"\u003cp\u003eNVIDIA RTX 5000 Ada Generation 32GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 32GB GDDR6\u003c\/li\u003e\n\u003cli\u003eBandwidth: ~576GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ada Lovelace architecture, 12,800 CUDA cores\u003c\/li\u003e\n\u003cli\u003ePerformance: high-end professional rendering and AI-accelerated design\u003c\/li\u003e\n\u003cli\u003eTDP: 250W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe 4.0, dual-slot\u003c\/li\u003e\n\u003cli\u003eIdeal for: high-end 3D design, rendering, simulation and AI workstation workloads\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726098379080,"sku":null,"price":5100.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-5g132-2240-000-rtx-5000-ada-bulk-pack.jpg?v=1790505166"},{"product_id":"900-5g132-2740-000-rtx-5000ada-retail-pack","title":"900-5G132-2740-000 NVIDIA RTX 5000 ADA (retail pack)","description":"\u003cp\u003eNVIDIA RTX 5000 Ada Generation 32GB GPU (new, retail-packaged).\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 32GB GDDR6\u003c\/li\u003e\n\u003cli\u003eBandwidth: ~576GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ada Lovelace architecture, 12,800 CUDA cores\u003c\/li\u003e\n\u003cli\u003ePerformance: high-end professional rendering and AI-accelerated design\u003c\/li\u003e\n\u003cli\u003eTDP: 250W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe 4.0, dual-slot\u003c\/li\u003e\n\u003cli\u003eIdeal for: high-end 3D design, rendering, simulation and AI workstation workloads\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726098444616,"sku":null,"price":5200.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/12.png?v=1787237622"},{"product_id":"900-5g133-2240-000-rtx5880ada-bulk-pack","title":"900-5G133-2240-000 NVIDIA RTX5880 ADA  (Bulk Pack)","description":"\u003cp\u003eNVIDIA RTX 5880 Ada Generation 48GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 48GB GDDR6\u003c\/li\u003e\n\u003cli\u003eBandwidth: ~960GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ada Lovelace architecture, 14,080 CUDA cores\u003c\/li\u003e\n\u003cli\u003ePerformance: flagship-tier professional rendering and AI-accelerated design\u003c\/li\u003e\n\u003cli\u003eTDP: 285W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe 4.0, dual-slot\u003c\/li\u003e\n\u003cli\u003eIdeal for: large-scene 3D rendering, simulation and AI workstation workloads\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726098542920,"sku":null,"price":6000.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-5g133-2240-000-rtx5880ada-bulk-pack.jpg?v=1790505169"},{"product_id":"900-5g133-2200-000-rtx-a6000-48gb-bulk-pack","title":"900-5G133-2200-000 NVIDIA RTX A6000 48GB (bulk pack) - NEW","description":"","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726098673992,"sku":"900-5G133-2200-000","price":5375.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-5g133-2200-000-rtx-a6000-48gb-bulk-pack.jpg?v=1790505168"},{"product_id":"900-5g133-2250-000-rtx-6000-ada-bulk-pack","title":"900-5G133-2250-000 NVIDIA RTX 6000 ADA (bulk pack)","description":"\u003cp\u003eNVIDIA RTX 6000 Ada Generation 48GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 48GB GDDR6 with ECC\u003c\/li\u003e\n\u003cli\u003eBandwidth: 960GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ada Lovelace architecture, 18,176 CUDA cores\u003c\/li\u003e\n\u003cli\u003ePerformance: flagship professional rendering and AI-accelerated design\u003c\/li\u003e\n\u003cli\u003eTDP: 300W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe 4.0, dual-slot\u003c\/li\u003e\n\u003cli\u003eIdeal for: large-scene 3D rendering, simulation and professional AI workstation workloads\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726099362120,"sku":"900-5G133-2250-000","price":8275.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/unnamed_2efc9465-f1f1-4da3-9a67-fd4dc2c64e03.jpg?v=1720146930"},{"product_id":"900-5g150-2500-000-rtx-8000","title":"900-5G150-2500-000 NVIDIA RTX 8000","description":"\u003cp\u003eNVIDIA Quadro RTX 8000 48GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 48GB GDDR6 with ECC\u003c\/li\u003e\n\u003cli\u003eBandwidth: ~672GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Turing architecture, 4,608 CUDA cores\u003c\/li\u003e\n\u003cli\u003ePerformance: professional rendering and ray tracing\u003c\/li\u003e\n\u003cli\u003eTDP: 260W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe 3.0, dual-slot\u003c\/li\u003e\n\u003cli\u003eIdeal for: professional 3D rendering, ray tracing and large-dataset visualization\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726099493192,"sku":null,"price":4600.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-5g150-2500-000-rtx-8000.jpg?v=1790505162"},{"product_id":"n409d3-246x-18332989-rtx4090d-x3","title":"N409D3-246X-18332989 NVIDIA RTX4090D X3","description":"\u003cp\u003eNVIDIA GeForce RTX 4090 24GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 24GB GDDR6X\u003c\/li\u003e\n\u003cli\u003eBandwidth: ~1,008GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ada Lovelace architecture, 16,384 CUDA cores\u003c\/li\u003e\n\u003cli\u003ePerformance: flagship consumer\/creator performance\u003c\/li\u003e\n\u003cli\u003eTDP: 450W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe 4.0, large dual\/triple-slot\u003c\/li\u003e\n\u003cli\u003eIdeal for: high-end content creation, AI development and gaming workloads\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726099525960,"sku":null,"price":8000.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/09abc1e7e6dc1d58e7b5a4ea704f1d81-1200x900.jpg?v=1724947924"},{"product_id":"rtx4090d-rtx4090d-hyper-brain","title":"RTX4090D Hyper Brain","description":"\u003cp\u003eNVIDIA GeForce RTX 4090 24GB GPU.\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 24GB GDDR6X\u003c\/li\u003e\n\u003cli\u003eBandwidth: ~1,008GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ada Lovelace architecture, 16,384 CUDA cores\u003c\/li\u003e\n\u003cli\u003ePerformance: flagship consumer\/creator performance\u003c\/li\u003e\n\u003cli\u003eTDP: 450W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe 4.0, large dual\/triple-slot\u003c\/li\u003e\n\u003cli\u003eIdeal for: high-end content creation, AI development and gaming workloads\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48726099657032,"sku":null,"price":1600.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/NVIDIA-GeForce-RTX-4090-D-Graphics-Card-Official.webp?v=1724947924"},{"product_id":"vcnrtxa5000-sb-pny-nvidia-rtx-a5000-oem-version","title":"VCNRTXA5000-SB PNY NVIDIA RTX A5000 OEM Version","description":"\u003cp\u003eVCNRTXA5000-SB PNY NVIDIA RTX A5000 OEM Version -\u003c\/p\u003e\n\u003cp\u003eCUDA Cores - 8192\u003c\/p\u003e\n\u003cp\u003eTensor Cores - 256\u003c\/p\u003e\n\u003cp\u003eRT Cores - 64\u003c\/p\u003e\n\u003cp\u003eSingle Precision Performance - 27.8 TFLOPS\u003c\/p\u003e\n\u003cp\u003eRT Core Performance - 54.2 TFLOPS\u003c\/p\u003e\n\u003cp\u003eTensor Performance - 222.2 TFLOPS\u003c\/p\u003e\n\u003cp\u003eGPU Memory - 24 GB GDDR6 with ECC\u003c\/p\u003e\n\u003cp\u003eMemory Interface - 384-bit\u003c\/p\u003e\n\u003cp\u003eMemory Bandwidth - 768 GB\/sec\u003c\/p\u003e\n\u003cp\u003eSystem Interface - PCI Express 4.0 x16\u003c\/p\u003e\n\u003cp\u003eDisplay Connectors - 4x DisplayPort 1.4a\u003c\/p\u003e\n\u003cp\u003eMaximum Power Consumption - 230 W\u003c\/p\u003e\n\u003c!----\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48765185491272,"sku":"VCNRTXA5000-SB","price":2400.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-vcnrtxa5000-sb-pny-nvidia-rtx-a5000-oem-version.jpg?v=1790505167"},{"product_id":"900-5g132-2240-000-nvidia-rtx-5000-ada-graphics-card","title":"900-5G132-2240-000 NVIDIA RTX 5000 Ada - Graphics Card","description":"\u003cp\u003e900-5G132-2240-000 NVIDIA RTX 5000 Ada -\u003c\/p\u003e\n\u003cp\u003eCUDA Cores - 12800\u003c\/p\u003e\n\u003cp\u003eTensor Cores - 400\u003c\/p\u003e\n\u003cp\u003eRT Cores - 100\u003c\/p\u003e\n\u003cp\u003eSingle Precision Performance - 65.3 TFLOPS\u003c\/p\u003e\n\u003cp\u003eRT Core Performance - 151.0 TFLOPS\u003c\/p\u003e\n\u003cp\u003eTensor Performance - 1,044.4 TFLOPS\u003c\/p\u003e\n\u003cp\u003eGPU Memory - 32GB of GDDR6 memory\u003c\/p\u003e\n\u003c!----\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48765348708680,"sku":"900-5G132-2240-000","price":5100.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-5g132-2240-000-nvidia-rtx-5000-ada-graphics-card.jpg?v=1790505170"},{"product_id":"nvidia-hpe-h100-94gb-nvl-900-21010-0320-030-new-3-year-warranty","title":"900-21010-0320-030 NVIDIA H100 NVL 94GB PCIe Accelerator - NEW - 3 YEAR WARRANTY","description":"\u003cp\u003eNvidia H100 NVL Tensor Core GPU 94GB Hopper Architecture Nvlink Dual Slot - NEW \u003c\/p\u003e\n\u003cp\u003eThe NVIDIA® H100 NVL Tensor Core GPU is the most optimized platform for LLM \u003cbr\u003eInferences with its high compute density, high memory bandwidth, high energy \u003cbr\u003eefficiency, and unique NVLink architecture. It also delivers unprecedented acceleration \u003cbr\u003eto power the world’s highest-performing elastic data centers for AI, data analytics, and \u003cbr\u003ehigh-performance computing (HPC) applications. NVIDIA H100 NVL Tensor Core \u003cbr\u003etechnology supports a broad range of math precisions, providing a single accelerator for \u003cbr\u003eevery compute workload. The NVIDIA H100 NVL supports double precision (FP64), singleprecision (FP32), half precision (FP16), 8-bit floating point (FP8), and integer (INT8) \u003cbr\u003ecompute tasks.\u003c\/p\u003e\n\u003cp\u003e\u003cbr\u003eThe NVIDIA H100 NVL card is a dual-slot 10.5 inch PCI Express Gen5 card based on the \u003cbr\u003eNVIDIA Hopper™ architecture. It uses a passive heat sink for cooling, which requires \u003cbr\u003esystem airflow to operate the card properly within its thermal limits. The NVIDIA H100 \u003cbr\u003eNVL operates unconstrained up to its maximum thermal design power (TDP) level of 400 \u003cbr\u003eW to accelerate applications that require the fastest computational speed and highest \u003cbr\u003edata throughput. The NVIDIA H100 NVL debuts the world’s highest PCIe card memory \u003cbr\u003ebandwidth of nearly 4,000 gigabytes per second (GBps). This speeds time to solution for \u003cbr\u003ethe largest models and most massive data sets.\u003c\/p\u003e\n\u003cp\u003e\u003cbr\u003eThe NVIDIA H100 NVL card features Multi-Instance GPU (MIG) capability. This can be \u003cbr\u003eused to partition the GPU into as many as seven hardware isolated GPU instances, \u003cbr\u003eproviding a unified platform that enables elastic data centers to adjust dynamically to \u003cbr\u003eshifting workload demands. As well as it can allocate the right size of resources from the \u003cbr\u003esmallest to biggest multi-GPU jobs. NVIDIA H100 NVL versatility means that IT managers \u003cbr\u003ecan maximize the utility of every graphics processing unit (GPU) in their data center.\u003cbr\u003eNVIDIA H100 NVL cards use three NVIDIA® NVLink® bridges. They are the same as the \u003cbr\u003eone used with NVIDIA H100 PCIe cards. This allows two NVIDIA H100 PCIe cards to be \u003cbr\u003econnected to deliver 600 GB\/s bidirectional bandwidth or 10x the bandwidth of PCIe \u003cbr\u003eGen4, to maximize application performance for large workloads\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":48786660294984,"sku":"900-21010-0320-030","price":23440.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/image-removebg-preview-2024-09-13T093312.816_bdfa1ffd-b0fe-4215-8359-7e7828ebdc50.png?v=1726216489"},{"product_id":"mellanox-nvidia-mcx75310aas-neat-connectx-7-400gbe-ndr-ib-single-port-osfp-hhhl-adapter-card-pcie-5-0-x16-crypto-disabled-secure-boot-enabled-new","title":"Mellanox Nvidia MCX75310AAS-NEAT ConnectX-7 400GbE\/NDR IB Single-Port OSFP HHHL Adapter Card - PCIe 5.0 x16, Crypto Disabled, Secure Boot Enabled - NEW","description":"\u003ch3\u003eMellanox Nvidia MCX75310AAS-NEAT ConnectX-7 400GbE\/NDR IB Single-Port OSFP HHHL Adapter Card - PCIe 5.0 x16, Crypto Disabled, Secure Boot Enabled - NEW\u003c\/h3\u003e\n\u003c!----\u003e","brand":"Mellanox","offers":[{"title":"Default Title","offer_id":48814443364680,"sku":"MCX75310AAS-NEAT","price":2150.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-mellanox-nvidia-mcx75310aas-neat-connectx-7-400gbe-ndr-ib-single-port-14d5ea.jpg?v=1790505156"},{"product_id":"900-2g193-0000-000-nvidia-l4-24gb","title":"900-2G193-0000-000 NVIDIA L4 24GB - New","description":"\u003cp\u003eNVIDIA L4 24GB GPU (new).\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 24GB GDDR6\u003c\/li\u003e\n\u003cli\u003eBandwidth: 300GB\/s\u003c\/li\u003e\n\u003cli\u003eCompute: Ada Lovelace architecture\u003c\/li\u003e\n\u003cli\u003ePerformance: 30.3 TFLOPS FP32, up to 242 TFLOPS FP16 Tensor (with sparsity)\u003c\/li\u003e\n\u003cli\u003eTDP: 72W\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe Gen4, 1-slot low-profile\u003c\/li\u003e\n\u003cli\u003eIdeal for: AI inference, video and graphics at data center to edge scale\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":49044195180872,"sku":null,"price":2850.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-2g193-0000-000-nvidia-l4-24gb.jpg?v=1790505149"},{"product_id":"s2d86c-nvidia-h100-nvl-94gb-pcie-accelerator-for-hpe-new-3-year-warranty","title":"S2D86C NVIDIA H100 NVL 94GB PCIe Accelerator for HPE - NEW - 3 YEAR WARRANTY","description":"\u003cp\u003eNVIDIA H100 NVL 94GB GPU (new).\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eMemory: 94GB HBM3 per card (188GB per 2-GPU kit)\u003c\/li\u003e\n\u003cli\u003eBandwidth: ~3.9TB\/s per card\u003c\/li\u003e\n\u003cli\u003eCompute: Hopper architecture, NVLink-bridged pair\u003c\/li\u003e\n\u003cli\u003ePerformance: up to 3,958 TFLOPS FP16 \/ 7,916 TFLOPS FP8 (pair, sparsity)\u003c\/li\u003e\n\u003cli\u003eTDP: 350-400W per card (configurable)\u003c\/li\u003e\n\u003cli\u003eForm factor: PCIe, dual-slot air-cooled, sold as NVLink-bridged pair\u003c\/li\u003e\n\u003cli\u003eWarranty: 3-year warranty\u003c\/li\u003e\n\u003cli\u003eIdeal for: large language model inference and training at scale\u003c\/li\u003e\n\u003c\/ul\u003e","brand":"HPE","offers":[{"title":"Default Title","offer_id":49446817399112,"sku":"S2D86C","price":26510.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/image-removebg-preview-2024-09-13T093312.816_5fefffee-5ae2-4aaf-a5e7-1af79a9e13e1.png?v=1726216452"},{"product_id":"gpu-nva100-80-nc-nvidia-a100-80gb-pcie-gpu-accelerator-new","title":"GPU-NVA100-80-NC NVIDIA  A100 80GB PCIe GPU Accelerator - NEW","description":"\u003cp\u003eThe NVIDIA® A100 80GB PCIe card delivers unprecedented acceleration to power the world’s \u003cbr\u003ehighest-performing elastic data centres for AI, data analytics, and high-performance \u003cbr\u003ecomputing (HPC) applications. NVIDIA A100 Tensor Core technology supports a broad range of math precisions, providing a single accelerator for every compute workload. The NVIDIA A100 80GB PCIe supports double precision (FP64), single precision (FP32), half precision (FP16), and integer (INT8) compute tasks.\u003c\/p\u003e\n\u003cp\u003e\u003cbr\u003eThe NVIDIA A100 80GB card is a dual-slot 10.5 inch PCI Express Gen4 card based on the \u003cbr\u003eNVIDIA Ampere GA100 graphics processing unit (GPU). It uses a passive heat sink for cooling, \u003cbr\u003ewhich requires system airflow to properly operate the card within its thermal limits. The \u003cbr\u003eNVIDIA A100 80GB PCIe operates unconstrained up to its maximum thermal design power \u003cbr\u003e(TDP) level of 300 W to accelerate applications that require the fastest computational speed \u003cbr\u003eand highest data throughput. The latest generation A100 80GB PCIe doubles GPU memory and debuts the world’s highest PCIe card memory bandwidth up to 1.94 terabytes per second \u003cbr\u003e(TB\/s), speeding time to solution for the largest models and most massive data sets. \u003cbr\u003eThe NVIDIA A100 80GB PCIe card features Multi-Instance GPU (MIG) capability, which can be \u003cbr\u003epartitioned into as many as seven isolated GPU instances, providing a unified platform that \u003cbr\u003eenables elastic data centers to dynamically adjust to shifting workload demands. When using \u003cbr\u003eMIG to partition an A100 GPU into up to seven smaller instances, A100 can readily handle \u003cbr\u003edifferent-sized acceleration needs, from the smallest job to the biggest multi-node workload. \u003cbr\u003eA100 80GB versatility means IT managers can maximize the utility of every GPU in their data \u003cbr\u003ecentre.\u003c\/p\u003e\n\u003cp\u003eNVIDIA A100 80GB PCIe cards use three NVIDIA® NVLink® bridges that allow multiple A100 \u003cbr\u003e80GB PCIe cards to be connected together to deliver 600 GB\/s bandwidth or 10x the bandwidth of PCIe Gen4, in order to maximize application throughput with the larger workloads.\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":50054380650824,"sku":"GPU-NVA100-80-NC","price":19420.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/900-21001-0020-000_1_1.jpg?v=1720136440"},{"product_id":"nva100tcgpu80-kit-nvidia-a100-80gb-pcie-gpu-accelerator-new","title":"NVA100TCGPU80-KIT NVIDIA A100 80GB PCIe GPU Accelerator - NEW","description":"\u003cp\u003eThe NVIDIA® A100 80GB PCIe card delivers unprecedented acceleration to power the world’s \u003cbr\u003ehighest-performing elastic data centres for AI, data analytics, and high-performance \u003cbr\u003ecomputing (HPC) applications. NVIDIA A100 Tensor Core technology supports a broad range of math precisions, providing a single accelerator for every compute workload. The NVIDIA A100 80GB PCIe supports double precision (FP64), single precision (FP32), half precision (FP16), and integer (INT8) compute tasks.\u003c\/p\u003e\n\u003cp\u003e\u003cbr\u003eThe NVIDIA A100 80GB card is a dual-slot 10.5 inch PCI Express Gen4 card based on the \u003cbr\u003eNVIDIA Ampere GA100 graphics processing unit (GPU). It uses a passive heat sink for cooling, \u003cbr\u003ewhich requires system airflow to properly operate the card within its thermal limits. The \u003cbr\u003eNVIDIA A100 80GB PCIe operates unconstrained up to its maximum thermal design power \u003cbr\u003e(TDP) level of 300 W to accelerate applications that require the fastest computational speed \u003cbr\u003eand highest data throughput. The latest generation A100 80GB PCIe doubles GPU memory and debuts the world’s highest PCIe card memory bandwidth up to 1.94 terabytes per second \u003cbr\u003e(TB\/s), speeding time to solution for the largest models and most massive data sets. \u003cbr\u003eThe NVIDIA A100 80GB PCIe card features Multi-Instance GPU (MIG) capability, which can be \u003cbr\u003epartitioned into as many as seven isolated GPU instances, providing a unified platform that \u003cbr\u003eenables elastic data centers to dynamically adjust to shifting workload demands. When using \u003cbr\u003eMIG to partition an A100 GPU into up to seven smaller instances, A100 can readily handle \u003cbr\u003edifferent-sized acceleration needs, from the smallest job to the biggest multi-node workload. \u003cbr\u003eA100 80GB versatility means IT managers can maximize the utility of every GPU in their data \u003cbr\u003ecentre.\u003c\/p\u003e\n\u003cp\u003eNVIDIA A100 80GB PCIe cards use three NVIDIA® NVLink® bridges that allow multiple A100 \u003cbr\u003e80GB PCIe cards to be connected together to deliver 600 GB\/s bandwidth or 10x the bandwidth of PCIe Gen4, in order to maximize application throughput with the larger workloads.\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":50054381535560,"sku":"NVA100TCGPU80-KIT","price":19420.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/900-21001-0020-000_1_1.jpg?v=1720136440"},{"product_id":"900-21001-0020-000-nvidia-a100-80gb-pcie-gpu-accelerator-new","title":"900-21001-0020-000 NVIDIA A100 80GB PCIe GPU Accelerator - NEW","description":"\u003cp class=\"font-claude-response-body break-words whitespace-normal\"\u003eThe NVIDIA® A100 80GB PCIe card delivers unprecedented acceleration to power the world's highest-performing elastic data centres for AI, data analytics, and high-performance computing (HPC) applications. NVIDIA A100 Tensor Core technology supports a broad range of math precisions, providing a single accelerator for every compute workload. The NVIDIA A100 80GB PCIe supports double precision (FP64), single precision (FP32), half precision (FP16), and integer (INT8) compute tasks.\u003c\/p\u003e\n\u003cp class=\"font-claude-response-body break-words whitespace-normal\"\u003eThe NVIDIA A100 80GB card is a dual-slot 10.5-inch PCI Express Gen4 card based on the NVIDIA Ampere GA100 graphics processing unit (GPU). It uses a passive heat sink for cooling, which requires system airflow to properly operate the card within its thermal limits. The NVIDIA A100 80GB PCIe operates unconstrained up to its maximum thermal design power (TDP) level of 300W to accelerate applications that require the fastest computational speed and highest data throughput. The latest generation A100 80GB PCIe doubles GPU memory and debuts the world's highest PCIe card memory bandwidth at up to 1.94 terabytes per second (TB\/s), speeding time to solution for the largest models and most massive datasets.\u003c\/p\u003e\n\u003cp class=\"font-claude-response-body break-words whitespace-normal\"\u003eThe NVIDIA A100 80GB PCIe card features Multi-Instance GPU (MIG) capability, which can be partitioned into as many as seven isolated GPU instances, providing a unified platform that enables elastic data centres to dynamically adjust to shifting workload demands. When using MIG to partition an A100 GPU into up to seven smaller instances, the A100 can readily handle different-sized acceleration needs, from the smallest job to the biggest multi-node workload. A100 80GB versatility means IT managers can maximise the utility of every GPU in their data centre.\u003c\/p\u003e\n\u003cp class=\"font-claude-response-body break-words whitespace-normal\"\u003eNVIDIA A100 80GB PCIe cards use three NVIDIA® NVLink® bridges that allow multiple A100 80GB PCIe cards to be connected together to deliver 600 GB\/s bandwidth — 10x the bandwidth of PCIe Gen4 — in order to maximise application throughput with larger workloads.\u003c\/p\u003e","brand":"NVIDIA","offers":[{"title":"Default Title","offer_id":50054382584136,"sku":"900-21001-0020-000","price":19420.0,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/files\/ei-900-21001-0020-000-nvidia-a100-80gb-pcie-gpu-accelerator-new.jpg?v=1790505146"}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0792\/5920\/5960\/collections\/image-removebg-preview_-_2024-09-04T160725.574_b53c0589-a306-4e96-8f5f-0460d80ed27c.png?v=1776257212","url":"https:\/\/etontechnology.com\/collections\/nvidia-gpus.oembed?page=5","provider":"Eton Technology Solutions","version":"1.0","type":"link"}