{"title":"Cisco GPU's","description":"","products":[{"product_id":"ucsc-gpu-vgxk2","title":"Cisco Nvidia Grid K2 | UCSC-GPU-VGXK2","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e   \u003cul\u003e\n\u003cli\u003eGPU Two GK104 GPUs\u003c\/li\u003e\n\u003cli\u003eNumber of processor cores: 1536 per GPU\u003c\/li\u003e\n\u003cli\u003eCore clock: 745 MHz Board\u003c\/li\u003e\n\u003cli\u003ePCI Express Gen3 ×16 system interface\u003c\/li\u003e\n\u003cli\u003ePhysical dimensions: 4.376 inches × 10.5 inches × 1.52 inches (dual-slot)\u003c\/li\u003e\n\u003cli\u003eBoard power: 225 W (maximum) Power Connectors\u003c\/li\u003e\n\u003cli\u003eOne 6-pin PCI Express power connector\u003c\/li\u003e\n\u003cli\u003eOne 8-pin PCI Express power connector Memory\u003c\/li\u003e\n\u003cli\u003eMemory clock: 2.5 GHz\u003c\/li\u003e\n\u003cli\u003eInterface: 256-bit\u003c\/li\u003e\n\u003cli\u003eTotal board memory: 8 GB (4 GB per GPU)\u003c\/li\u003e\n\u003cli\u003e32 pieces of 128M × 16 GDDR5, SDRAM (per GPU) BIOS\u003c\/li\u003e\n\u003cli\u003e2 MBit Serial ROM Virtualization Solutions\u003c\/li\u003e\n\u003cli\u003eCitrix XenServer + XenDesktop with HDX 3D Pro\u003c\/li\u003e\n\u003cli\u003eCitrix XenServer with NVIDIA NVIDIA GRID Hypervisor + XenDesktop with HDX\u003c\/li\u003e\n\u003cli\u003eMicrosoft Windows Server 2012 + RemoteFX\u003c\/li\u003e\n\u003cli\u003eMicrosoft Windows Server 2008 R2 + RemoteFX\u003c\/li\u003e\n\u003cli\u003eVMware ESXi + View with vSGA\u003c\/li\u003e\n\u003c\/ul\u003e\n  \u003chr\u003e\n  \u003cp\u003eThe NVIDIA GRID™ K2 is a dual-slot 10.5 inch PCI Express Gen3 graphics card with two high-end NVIDIA® Kepler™ graphics processing units (GPUs). The NVIDIA GRID K2 has 8 GB of GDDR5 memory (4 GB per GPU), and a 225 W maximum power limit. The NVIDIA GRID K2 graphics board uses a passive heat sink that requires system airflow to properly operate the card within thermal limits. It is designed to accelerate graphics in virtual remote workstation and virtual desktop environments. \u003cbr\u003e\u003cbr\u003eThe NVIDIA GRID K2 graphics board can be configured to enable or disable ECC (error correcting codes) that can fix single-bit errors and detect double-bit errors. Enabling ECC will cause some of the memory to be used for the ECC bits, so the user available memory will decrease by 10%. ECC protection is for DRAM only.\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":32993086963797,"sku":"UCSC-GPU-VGXK2","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/UCSC-GPU-VGXK2.jpg?v=1664912894"},{"product_id":"ucsc-gpu-7150x2","title":"Cisco AMD Firepro S7150X2 | UCSC-GPU-7150X2","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cp\u003eThe AMD FirePro™ family of hardware-virtualized GPUs with Multiuser GPU (MxGPU) technology delivers a simple, secure and cost effective solution for high performance virtual workstations.\u003c\/p\u003e\n  \u003chr\u003e\n\u003cp\u003e\u003cb\u003eNumber of Concurrent Users Supported\u003c\/b\u003e : Up to 32\u003cbr\u003e\u003cb\u003eMemory: \u003c\/b\u003e16 GB GDDR5 (2 x 8GB)\u003cbr\u003e\u003cb\u003eMemory Bandwidth: \u003c\/b\u003e256 bit\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":32993086996565,"sku":"UCSC-GPU-7150X2","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/UCSC-GPU-7150X2.jpg?v=1664910957"},{"product_id":"ucsc-gpu-k801","title":"Cisco Nvidia K80 | UCSC-GPU-K80","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cp\u003e The NVIDIA \u003csup\u003e®\u003c\/sup\u003e Tesla \u003csup\u003e®\u003c\/sup\u003e K80 Accelerator dramatically lowers data center costs by delivering exceptional performance with fewer, more powerful servers. It's engineered to boost throughput in real-world applications by 5-10x, while also saving customers up to 50% for an accelerated data center compared to a CPU-only system. This increased throughput means more scientific discoveries delivered to researchers every day, or better user engagement for web services.\u003cbr\u003e\u003cbr\u003e \u003c\/p\u003e\n\u003chr\u003e\n\u003cul\u003e\n\u003cli\u003e4992 NVIDIA CUDA cores with a dual-GPU design\u003c\/li\u003e\n\u003cli\u003eUp to 2.91 teraflops double-precision performance with NVIDIA GPU Boost\u003c\/li\u003e\n\u003cli\u003eUp to 8.73 teraflops single-precision performance with NVIDIA GPU Boost\u003c\/li\u003e\n\u003cli\u003e24 GB of GDDR5 memory\u003c\/li\u003e\n\u003cli\u003e480 GB\/s aggregate memory bandwidth\u003c\/li\u003e\n\u003cli\u003eECC protection for increased reliability\u003c\/li\u003e\n\u003cli\u003eServer-optimized to deliver the best throughput in the data center\u003c\/li\u003e\n\u003c\/ul\u003e \u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":32993087029333,"sku":"UCSC-GPU-K80","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/UCSC-GPU-K801.jpg?v=1664911102"},{"product_id":"ucsc-gpu-m601","title":"Nvidia® Tesla® M60 GPU Accelerator | UCSC-GPU-M60","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cp\u003eThe NVIDIA Tesla M60 GPU accelerator works with NVIDIA GRID software to provide the industry’s highest user performance for virtualized workstations, desktops, and applications. This solution allows enterprises to virtualize any application—including professional graphics applications—and deliver them out to any device, anywhere.\u003c\/p\u003e\n\u003cp\u003e\u003cb\u003eVirtualization Use Case\u003c\/b\u003e Performance-Optimized Graphics Virtualization \u003cbr\u003e\u003cb\u003eGPU Architecture\u003c\/b\u003e NVIDIA Maxwell™ \u003cbr\u003e\u003cb\u003eGPUs per Board\u003c\/b\u003e 2 \u003cbr\u003e\u003cb\u003eMax User per Board\u003c\/b\u003e 32 (16 per GPU) \u003cbr\u003e\u003cb\u003eNVIDIA CUDA® Cores\u003c\/b\u003e 4096 NVIDIA CUDA Cores (2048 per GPU) \u003cbr\u003e\u003cb\u003eGPU Memory\u003c\/b\u003e 16 GB of GDDR5 Memory (8 per GPU) \u003cbr\u003e\u003cb\u003eH.264 1080p30 streams\u003c\/b\u003e 36 \u003cbr\u003e\u003cb\u003eMax Power Consumption\u003c\/b\u003e 300 W \u003cbr\u003e\u003cb\u003eThermal Solution\u003c\/b\u003e Active\/Passive \u003cbr\u003e\u003cb\u003eForm Factor\u003c\/b\u003e PCIe 3.0 Dual Slot\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":32993087094869,"sku":"UCSC-GPU-M60","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/UCSC-GPU-K801_41aec2b3-603f-4951-811d-54c2eb9b22f3.jpg?v=1664911834"},{"product_id":"ucsc-gpu-p100-12g","title":"Cisco Nvidia P100 12GB | UCSC-GPU-P100-12G","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cp\u003eToday's data centers rely on many interconnected commodity compute nodes, which limits high performance computing (HPC) and hyperscale workloads. NVIDIA \u003csup\u003e®\u003c\/sup\u003e Tesla \u003csup\u003e®\u003c\/sup\u003e P100 taps into NVIDIA Pascal\u003csup\u003e™\u003c\/sup\u003e GPU architecture to deliver a unified platform for accelerating both HPC and AI, dramatically increasing throughput while also reducing costs.\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":32993087127637,"sku":"UCSC-GPU-P100-12G","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/UCSC-GPU-P100-16G_9612c60c-778d-4a5b-9d38-1b94dad059a5.jpg?v=1664912019"},{"product_id":"ucsc-gpu-p100-16g","title":"Cisco UCS Nvidia P100 16GB GPU  | UCSC-GPU-P100-16G","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cp\u003eToday's data centers rely on many interconnected commodity compute nodes, which limits high performance computing (HPC) and hyperscale workloads. NVIDIA \u003csup\u003e®\u003c\/sup\u003e Tesla \u003csup\u003e® \u003c\/sup\u003e P100 taps into NVIDIA Pascal\u003csup\u003e™\u003c\/sup\u003e GPU architecture to deliver a unified platform for accelerating both HPC and AI, dramatically increasing throughput while also reducing costs.\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":32993087160405,"sku":"UCSC-GPU-P100-16G","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/UCSC-GPU-P100-16G.jpg?v=1664910702"},{"product_id":"ucsb-gpu-m6-4","title":"Cisco Ucs Blade Server M6 GPU - Grid 2.0 SW Required For VDI | UCSB-GPU-M6=","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cp\u003eUCS Blade Server M6 GPU - GRID 2.0 SW required for VDI\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":32993089912917,"sku":"UCSB-GPU-M6=","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/UCSB-GPU-M6_9a3d5ee6-4a03-43bf-9673-c19277f834a3.jpg?v=1668201481"},{"product_id":"ucsc-gpu-t4-16-nvidia-t4-16gb-low-profile-single-width-gpu","title":"Nvidia T4 16GB Low Profile Single-Width GPU | UCSC-GPU-T4-16","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cp\u003eThe NVIDIA \u003csup\u003e®\u003c\/sup\u003e T4 GPU accelerates diverse cloud workloads, including high-performance computing, deep learning training and inference, machine learning, data analytics, and graphics. Based on the new NVIDIA Turing \u003csup\u003e™\u003c\/sup\u003e architecture and packaged in an energy-efficient 70-watt, small PCIe form factor, T4 is optimized for mainstream computing environments and features multi-precision Turing Tensor Cores and new RT Cores. Combined with accelerated containerized software stacks from NGC, T4 delivers revolutionary performance at scale.\u003c\/p\u003e\n  \u003chr\u003e\n  \u003cb\u003eSPECIFICATIONS \u003c\/b\u003e\n\u003cul\u003e\n\u003cli\u003eGPU Architecture NVIDIA Turing\u003c\/li\u003e\n\u003cli\u003eNVIDIA Turing Tensor Cores 320\u003c\/li\u003e\n\u003cli\u003eNVIDIA CUDA ® Cores 2,560\u003c\/li\u003e\n\u003cli\u003eSingle-Precision 8.1 TFLOPS\u003c\/li\u003e\n\u003cli\u003eMixed-Precision (FP16\/FP32) 65 TFLOPS\u003c\/li\u003e\n\u003cli\u003eINT8 130 TOPS\u003c\/li\u003e\n\u003cli\u003eINT4 260 TOPS\u003c\/li\u003e\n\u003cli\u003eGPU Memory 16 GB GDDR6 | 300 GB\/sec\u003c\/li\u003e\n\u003cli\u003eECC Yes\u003c\/li\u003e\n\u003cli\u003eInterconnect\u003c\/li\u003e\n\u003cli\u003eBandwidth 32 GB\/sec\u003c\/li\u003e\n\u003cli\u003eSystem Interface x16 PCIe Gen3\u003c\/li\u003e\n\u003cli\u003eForm Factor Low-Profile PCIe\u003c\/li\u003e\n\u003cli\u003eThermal Solution Passive\u003c\/li\u003e\n\u003cli\u003eCompute APIs CUDA, NVIDIA TensorRT ™ , ONNX\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":40333744668757,"sku":"UCSC-GPU-T4-16","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/UCSC-GPU-T4-16.jpg?v=1664912769"},{"product_id":"ucsc-gpu-p4-nvidia-p4-low-profile-single-width-gpu","title":"Cisco Nvidia P4 Low Profile Single-Width GPU | UCSC-GPU-P4","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cul\u003e\n\u003cli\u003eSmall form-factor, 75-Watt design fits any scale-out server.\u003c\/li\u003e\n\u003cli\u003eINT8 operations slash latency by 15X.\u003c\/li\u003e\n\u003cli\u003eHardware-decode engine capable of transcoding and inferencing 35 HD video streams in real time.\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGPUArchitecture\u003c\/b\u003e NVIDIA Pascal™\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eSingle-Precision Performance\u003c\/b\u003e 5.5 TeraFLOPS*\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eInteger Operations (INT8)\u003c\/b\u003e 22 TOPS* (TeraOperations per Second)\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGPU Memory\u003c\/b\u003e 8 GB\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMemory Bandwidth\u003c\/b\u003e 192 GB\/s\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eSystem Interface\u003c\/b\u003e Low-Profile PCI Express Form Factor\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMax Power\u003c\/b\u003e 75W\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eEnhanced Programmability with Page Migration Engine\u003c\/b\u003e Yes\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eECC Protection\u003c\/b\u003e Yes\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eServer-Optimized for Data Center Deployment\u003c\/b\u003e Yes\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eHardware-Accelerated Video Engine\u003c\/b\u003e 1x Decode Engine, 2x Encode Engine\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003chr\u003e\n\u003cp\u003eThe NVIDIA Tesla P4 is powered by the revolutionary NVIDIA Pascal™ architecture and purpose-built to boost efficiency for scale-out servers running deep learning workloads, enabling smart responsive AI-based services. It slashes inference latency by 15X in any hyperscale infrastructure and provides an incredible 60X better energy efficiency than CPUs. This unlocks a new wave of AI services previous impossible due to latency limitations.\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":40333744701525,"sku":"UCSC-GPU-P4","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/UCSC-GPU-P4.jpg?v=1664912370"},{"product_id":"ucsc-gpu-t4-16-nvidia-t4-16gb-low-profile-single-width-gpu-spare-part","title":"Nvidia T4 16GB Low Profile Single-Width GPU Spare Part | UCSC-GPU-T4-16=","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cb\u003eCard Size\u003c\/b\u003e: Low Profile Single-Width\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMaximum\u003c\/b\u003e: 2\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003chr\u003e\n\u003cp\u003eThe NVIDIA T4 enterprise GPU supercharges the world's most trusted mainstream servers, easily fitting into standard data center infrastructures. Its low-profile, 70-watt (W) design is powered by NVIDIA Turing Tensor Cores, delivering revolutionary multi-precision performance to accelerate a wide range of modern applications, including machine learning, deep learning, and virtual desktops. This advanced GPU is packaged in an energy-efficient 70 W small PCIe form factor, optimized for maximum utility in enterprise data centers and the cloud.\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":40337228038229,"sku":"UCSC-GPU-T4-16=","price":0.0,"currency_code":"USD","in_stock":true}]},{"product_id":"ucsc-gpu-m10-nvidia-m10","title":"Nvidia M10 | UCSC-GPU-M10","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cp\u003e The NVIDIA \u003csup\u003e®\u003c\/sup\u003e M10 GPU works with NVIDIA GRID \u003csup\u003e® \u003c\/sup\u003e software to deliver the industry's highest user density for virtualized desktops and applications. It supports up to 32 users per board (1GB profile), up to 96 users per server, giving businesses the power to deliver great experiences to all of their employees at an affordable cost.\u003cbr\u003e\u003cbr\u003e \u003c\/p\u003e\n\u003chr\u003e\n\u003cul\u003e\n\u003cli\u003eFour NVIDIA Maxwell\u003csup\u003e™\u003c\/sup\u003e GPUs\u003c\/li\u003e\n\u003cli\u003eUp to 32 users per board\u003c\/li\u003e\n\u003cli\u003e2560 NVIDIA CUDA\u003csup\u003e®\u003c\/sup\u003e cores (640 per GPU)\u003c\/li\u003e\n\u003cli\u003e32 GB of GDDR5 memory (8 per GPU)\u003c\/li\u003e\n\u003cli\u003e28 H.264 1080p30 streams\u003c\/li\u003e\n\u003cli\u003eECC protection for increased reliability\u003c\/li\u003e\n\u003cli\u003eServer optimization to deliver the best throughput in the data center\u003c\/li\u003e\n\u003c\/ul\u003e \u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":40339661914197,"sku":"UCSC-GPU-M10","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/UCSC-GPU-M10.jpg?v=1664911332"},{"product_id":"ucsc-gpu-m10-nvidia-m10-spare-part","title":"Cisco Nvidia M10 Spare Part | UCSC-GPU-M10=","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cp\u003eNVIDIA M10\u003cbr\u003eCard Size: Full-Height Dual Width\u003cbr\u003eMax cards per node: 2\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":40345155731541,"sku":"UCSC-GPU-M10=","price":0.0,"currency_code":"USD","in_stock":true}]},{"product_id":"ucsc-gpu-p4-nvidia-p4-low-profile-single-width-gpu-spare-part","title":"Nvidia P4 Low Profile Single-Width GPU Spare Part | UCSC-GPU-P4=","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cul\u003e\n\u003cli\u003e\n\u003cb\u003eCard Size\u003c\/b\u003e: Low Profile Single-Width\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMaximum\u003c\/b\u003e: 2\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003chr\u003e\n\u003cp\u003eThe NVIDIA P4 is powered by the NVIDIA Pascal architecture and purpose-built to boost efficiency for scale-out servers, running deep learning workloads, enabling smart responsive AI-based services. It slashes inference latency in any hyperscale infrastructure and provides an incredible energy efficiency. This unlocks another wave of AI services previous impossible due to latency limitations.\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":40351801016405,"sku":"UCSC-GPU-P4=","price":0.0,"currency_code":"USD","in_stock":true}]},{"product_id":"ucsc-gpu-m60-nvidia-tesla-m60-spare-part","title":"Nvidia Tesla M60 Spare Part | UCSC-GPU-M60=","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cp\u003eNVIDIA Tesla M60\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":40351801573461,"sku":"UCSC-GPU-M60=","price":0.0,"currency_code":"USD","in_stock":true}]},{"product_id":"copy-of-ucsc-gpu-k801-nvidia-k80","title":"Cisco Nvidia M10 | UCSC-GPU-M102","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cp\u003eNVIDIA M10\u003cbr\u003eFull-Height, double wide\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":40374780526677,"sku":"UCSC-GPU-M102","price":0.0,"currency_code":"USD","in_stock":true}]},{"product_id":"ucsc-gpu-vgxk1","title":"Cisco Nvidia Grid K1 GPU | UCSC-GPU-VGXK1","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cul class=\"margin-empty margin-bottom\"\u003e\n\u003cli\u003e\n\u003cb\u003eModel\u003c\/b\u003e: NVIDIA GRID K1\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eForm Factor\u003c\/b\u003e: Dual-slot PCIe Gen3 x16\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eCUDA Cores\u003c\/b\u003e: 768 (192 per GPU)\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGPU Count\u003c\/b\u003e: 4 Kepler-based GPUs on a single board\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMemory\u003c\/b\u003e: 16 GB DDR3 (4 GB per GPU)\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003ePower Consumption\u003c\/b\u003e: 130W TDP\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eCooling\u003c\/b\u003e: Passive cooling (requires chassis airflow)\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eUse Case\u003c\/b\u003e: Virtual desktop deployments with moderate graphics needs (office apps, video playback, etc.)\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eSupported Users\u003c\/b\u003e: Up to 4 users per card (1 per GPU), scalable with vGPU software\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003chr\u003e\n\u003cp\u003eThe NVIDIA GRID K1 is a graphics processing unit (GPU) designed specifically for virtual desktop infrastructure (VDI) and virtualized environments. It enables multiple users to share a single physical GPU, delivering excellent graphics performance for business applications while improving resource utilization in data centers.\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":40376611602517,"sku":"UCSC-GPU-VGXK1","price":94.99,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/Nvidia-UCSC-GPU-VGXK1---3_85e72631-9224-4264-9469-acf5a0922dbd.jpg?v=1743534903"},{"product_id":"ucsc-gpu-k40-nvidia-tesla-k40","title":"Cisco Nvidia Tesla K40 | UCSC-GPU-K40","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cp\u003eNVIDIA Tesla K40\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":40376613175381,"sku":"UCSC-GPU-K40","price":0.0,"currency_code":"USD","in_stock":true}]},{"product_id":"ucsb-gpu-m6","title":"Cisco Nvidia M6 Mezzanine GPU | UCSB-GPU-M6","description":"\u003cdiv class=\"product-section container jc-between-center is-flex-row\"\u003e\n\u003cdiv class=\"twelve columns medium-down--one-whole-NG product-section-extras quick-specs\"\u003e \u003cdiv class=\"quick-specs-data\"\u003e \u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cul class=\"margin-empty margin-bottom\"\u003e\n\u003cli\u003e\n\u003cb\u003eTarget Server\u003c\/b\u003e: UCS B200\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eForm Factor\u003c\/b\u003e: Installed into mezzanine slot 2\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eUse Case\u003c\/b\u003e: Optimized for Virtual Desktop Infrastructure (VDI) scenarios using NVIDIA GRID 2.0A\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eSoftware\u003c\/b\u003e: Requires GRID software license for full virtualization support\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eSlot\u003c\/b\u003e: Slot 2 must remain exclusive to the GPU\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eUse Case Target\u003c\/b\u003e: Designed for VDI (Virtual Desktop Infrastructure) environments\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"four-NG column product-section-extras ideal-for\"\u003e\n\u003cdiv class=\"hfour\"\u003ePart Number: \u003c\/div\u003e\n\u003cul\u003e\u003cli\u003eUCSB-GPU-M6\u003c\/li\u003e\u003c\/ul\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\u003cdiv class=\"product-section container jc-between-center is-flex-row\"\u003e\n\u003cdiv class=\"eight medium-down--one-whole-NG \"\u003e\u003cp\u003eThe NVIDIA M6 GPU is a blade-optimized graphics card tailored for virtualized environments. Installed into mezzanine slot 2 of the Cisco UCS B200 M4 Blade Server, it delivers advanced graphics acceleration ideal for VDI (Virtual Desktop Infrastructure) and other compute-visual applications. The M6 card uses NVIDIA GRID 2.0 software to deliver GPU virtualization, enabling multiple users to share GPU resources securely. It supports hardware-accelerated graphics with low latency and is bundled with a custom standoff and wrench for secure installation. When installed, the card requires exclusive access to its slot and must not be combined with other adapters like VIC 1380 or port expanders.\u003c\/p\u003e\u003c\/div\u003e\n\u003cdiv class=\"eight medium-down--one-whole-NG \"\u003e\u003cp\u003eIn the Cisco UCS B200 M4 ecosystem, the NVIDIA M6 enables high-performance desktop virtualization in dense data center environments. Since the M6 occupies slot 2, administrators must route all I\/O through a compatible VIC card—typically the VIC 1340 or 1240—installed in the mLOM slot. These VICs are only compatible with the 6200 and 6300 Series Fabric Interconnects, setting strict hardware constraints for successful deployment. This architecture allows the B200 M4 server to provide rich user experiences in remote desktop and CAD-heavy environments, while maintaining Cisco’s blade server density and management efficiency.\u003c\/p\u003e\u003c\/div\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":40378437959765,"sku":"UCSB-GPU-M6","price":194.99,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/Cisco-UCSB-GPU-M6---8.jpg?v=1744141757"},{"product_id":"cisco-nvidia-tesla-a10-passive-150w-24gb-ucsc-gpu-a10","title":"Cisco Nvidia Tesla A10, Passive, 150W, 24GB GPU | UCSC-GPU-A10","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cul\u003e\n\u003cli\u003eAll GPU cards must be procured from Cisco as there is a unique SBIOS ID required by CIMC and UCSM\u003c\/li\u003e\n\u003cli\u003eSlots 4, 5, and 6 on riser card 2A accommodate single-wide GPUs\u003c\/li\u003e\n\u003cli\u003eSingle-wide\u003c\/li\u003e\n\u003cli\u003e150W\u003c\/li\u003e\n\u003cli\u003e24GB\u003c\/li\u003e\n\u003cli\u003eCisco C240 M6 Riser 2 (Gen 4)\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":47156122452280,"sku":"UCSC-GPU-A10","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/A10_869b0362-1287-445a-9ac8-3769c9d4ea7d.jpg?v=1697062376"},{"product_id":"cisco-nvidia-tesla-a16-dw-ucsc-gpu-a16","title":"Cisco Nvidia Tesla A16 DW GPU | UCSC-GPU-A16=","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cul class=\"margin-empty margin-bottom\"\u003e\n\u003cli\u003eAll GPU cards must be procured from Cisco as there is a unique SBIOS ID required by CIMC and UCSM\u003c\/li\u003e\n\u003cli\u003eNVIDIA Double Wide GPUs are supported\u003c\/li\u003e\n\u003cli\u003eThis GPU requires x16 support.\u003c\/li\u003e\n\u003cli\u003eThis GPU can be populated in Riser 1A slot 2 (x16), Riser 2A slot 5 (x16), and Riser 3C slot 7 (x16).\u003c\/li\u003e\n\u003cli\u003eEach server can support three of these GPUs.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":47156175372600,"sku":"UCSC-GPU-A16=","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/A16_278ae5f6-00b8-4bed-a02e-0ca46dbc6792.jpg?v=1697063152"},{"product_id":"cisco-nvidia-tesla-a30-dw-ucsc-gpu-a30","title":"Cisco Nvidia Tesla A30 DW GPU | UCSC-GPU-A30=","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cul class=\"margin-empty margin-bottom\"\u003e\n\u003cli\u003eAll GPU cards must be procured from Cisco as there is a unique SBIOS ID required by CIMC and UCSM\u003c\/li\u003e\n\u003cli\u003eNVIDIA Double Wide GPUs are supported\u003c\/li\u003e\n\u003cli\u003eThis GPU requires x16 support.\u003c\/li\u003e\n\u003cli\u003eThis GPU can be populated in Riser 1A slot 2 (x16), Riser 2A slot 5 (x16), and Riser 3C slot 7 (x16).\u003c\/li\u003e\n\u003cli\u003eEach server can support three of these GPUs.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":47156186349880,"sku":"UCSC-GPU-A30=","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/A30_2fe64cf0-2008-46e6-ac86-04eeb3453be2.jpg?v=1697063524"},{"product_id":"cisco-nvidia-tesla-a40-dw-ucsc-gpu-a40","title":"Cisco Nvidia Tesla A40 DW GPU | UCSC-GPU-A40","description":"\u003cdiv class=\"product-default-container\"\u003e\n        \u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n        \u003chr\u003e\n        \u003cul class=\"margin-empty margin-bottom\"\u003e\n\u003cli\u003eAll GPU cards must be procured from Cisco as there is a unique SBIOS ID required by CIMC and UCSM\u003c\/li\u003e\n\u003cli\u003eNVIDIA Double Wide GPUs are supported\u003c\/li\u003e\n\u003cli\u003eThis GPU requires x16 support.\u003c\/li\u003e\n\u003cli\u003eThis GPU can be populated in Riser 1A slot 2 (x16), Riser 2A slot 5 (x16), and Riser 3C slot 7 (x16).\u003c\/li\u003e\n\u003cli\u003eEach server can support three of these GPUs.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":47156192215352,"sku":"UCSC-GPU-A40","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/A40_6c33686d-2454-4d22-b4a3-3f218fafeba6.jpg?v=1697063529"},{"product_id":"cisco-nvidia-tesla-a100-dw-ucsc-gpu-a100","title":"Cisco Nvidia Tesla A100 DW  GPU | UCSC-GPU-A100=","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cul\u003e\n  \u003cli\u003eAll GPU cards must be procured from Cisco as there is a unique SBIOS ID required by CIMC and UCSM\u003c\/li\u003e\n  \u003cli\u003eNVIDIA Double Wide GPUs are supported\u003c\/li\u003e\n  \u003cli\u003eThis GPU requires x16 support.\u003c\/li\u003e\n  \u003cli\u003eThis GPU can be populated in Riser 1A slot 2 (x16), Riser 2A slot 5 (x16), and Riser 3C slot 7 (x16).\u003c\/li\u003e\n  \u003cli\u003eEach server can support three of these GPUs.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":47156197359928,"sku":"UCSC-GPU-A100=","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/A100-pci_613a613d-9076-4b03-b759-bec2fa038c79.jpg?v=1697063536"},{"product_id":"cisco-nvidia-tesla-a100-80gb-dw-ucsc-gpu-a100-80","title":"Cisco Nvidia Tesla A100 80GB DW GPU | UCSC-GPU-A100-80=","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cul\u003e\n  \u003cli\u003eAll GPU cards must be procured from Cisco as there is a unique SBIOS ID required by CIMC and UCSM\u003c\/li\u003e\n\u003cli\u003eNVIDIA Double Wide GPUs are supported\u003c\/li\u003e\n  \u003cli\u003eThis GPU requires x16 support.\u003c\/li\u003e\n  \u003cli\u003eThis GPU can be populated in Riser 1A slot 2 (x16), Riser 2A slot 5 (x16), and Riser 3C slot 7 (x16).\u003c\/li\u003e\n  \u003cli\u003eEach server can support three of these GPUs.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":47156200767800,"sku":"UCSC-GPU-A100-80=","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/A100-pci_960867b2-d284-4a27-874f-a01ac174d9e5.jpg?v=1697063546"},{"product_id":"cisco-nvidia-l4-tensor-core-gpu-72w-24gb-pcie-accelerator-ucsc-gpu-l4","title":"Cisco Nvidia L4 Tensor Core 72W 24GB GPU | UCSC-GPU-L4","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \n  \u003cp\u003eThe NVIDIA L4 Tensor Core GPU powered by the NVIDIA Ada Lovelace architecture delivers universal, energy-efficient acceleration for video, AI, visual computing, graphics, virtualization, and more. Packaged in a low-profile form factor, L4 is a cost-effective, energy-efficient solution for high throughput and low latency in every server, from the edge to the data center to the cloud. \u003c\/p\u003e\n\u003chr\u003e\n\u003cdiv class=\"table-mobile\"\u003e\n  \u003ctable\u003e\n\u003cthead\u003e\u003ctr\u003e\n\u003cth\u003eForm Factor\u003c\/th\u003e\n\u003cth\u003eL4\u003c\/th\u003e\n\u003c\/tr\u003e\u003c\/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eFP32\u003c\/td\u003e\n\u003ctd\u003e30.3 teraFLOPs\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eTF32 Tensor Core\u003c\/td\u003e\n\u003ctd\u003e120 teraFLOPS*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eFP16 Tensor Core\u003c\/td\u003e\n\u003ctd\u003e242 teraFLOPS*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eBFLOAT16 Tensor Core\u003c\/td\u003e\n\u003ctd\u003e242 teraFLOPS*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eFP8 Tensor Core\u003c\/td\u003e\n\u003ctd\u003e485 teraFLOPs*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eINT8 Tensor Core\u003c\/td\u003e\n\u003ctd\u003e485 TOPs*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eGPU memory\u003c\/td\u003e\n\u003ctd\u003e24GB\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eGPU memory bandwidth\u003c\/td\u003e\n\u003ctd\u003e300GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNVENC | NVDEC | JPEG decoders\u003c\/td\u003e\n\u003ctd\u003e2 | 4 | 4\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMax thermal design power (TDP)\u003c\/td\u003e\n\u003ctd\u003e72W\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eForm factor\u003c\/td\u003e\n\u003ctd\u003e1-slot low-profile, PCIe\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eInterconnect\u003c\/td\u003e\n\u003ctd\u003ePCIe Gen4 x16 64GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eServer options\u003c\/td\u003e\n\u003ctd\u003ePartner and NVIDIA-Certified Systems with 1–8 GPUs\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49567470223672,"sku":"UCSC-GPU-L4","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/L4_2cc52bb8-b20e-43ea-b9fe-70a5866d8806.jpg?v=1698789001"},{"product_id":"cisco-intel-flex-140-75w-sw-gpu-ucsc-gpu-flex140","title":"Cisco Intel Flex 140 75W SW GPU | UCSC-GPU-FLEX140","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\t\u003cul class=\"margin-empty\"\u003e\t\u003cli\u003e\n\u003cb\u003eManufacturer\u003c\/b\u003e: Intel\u003c\/li\u003e\t\u003cli\u003e\n\u003cb\u003eModle\u003c\/b\u003e: Flex 140\u003c\/li\u003e\t\u003cli\u003e\n\u003cb\u003eWattage\u003c\/b\u003e: 75w\u003c\/li\u003e\t\u003cli\u003e\n\u003cb\u003eForm Factor\u003c\/b\u003e: HHHL Single Wide\u003c\/li\u003e\t\u003c\/ul\u003e\n\u003chr\u003e\n\u003cp\u003eAll GPU cards must be procured from Cisco as there is a unique SBIOS IDrequired by CIMC and UCSM\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49567475269944,"sku":"UCSC-GPU-FLEX140","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/L4_2cc52bb8-b20e-43ea-b9fe-70a5866d8806.jpg?v=1698789001"},{"product_id":"cisco-ucs-nvidia-tesla-t4-16gb-x16-pci-e-70w-sw-hh-hl-gpu-ucsx-gpu-t4-16","title":"Cisco Ucs Nvidia Tesla T4 16GB x16  PCI-e 70W SW HH\/HL GPU | UCSX-GPU-T4-16","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cul\u003e\n\u003cli\u003e\n\u003cb\u003eModel\u003c\/b\u003e: T4 \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGPU Memory\u003c\/b\u003e: 16 GB GDDR6 \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMemory ECC\u003c\/b\u003e: Y \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMemory Bandwidth\u003c\/b\u003e: 300 GB\/sec \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMax Power Consumption\u003c\/b\u003e: 70W \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGraphic Bus \/ System Interface\u003c\/b\u003e: PCIe Gen3x16 \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eInterconnect Bandwidth\u003c\/b\u003e: 32 GB\/sec (PCIe 3.0) \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eSlot Width\u003c\/b\u003e: SW \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGPU Height \/ Length\u003c\/b\u003e: HHHL \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eAuxiliary Cable\u003c\/b\u003e: N\/A \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eWorkload\u003c\/b\u003e: Inferencing\/Edge\/VDI \u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49588337836344,"sku":"UCSX-GPU-T4-16","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/nvidia-tesla-t4_b120c7be-c8d6-41ad-9d60-1646c6670bf5.jpg?v=1676588264"},{"product_id":"cisco-nvidia-a16-64gb-250w-dw-fh-hl-gpu-ucsx-gpu-a16","title":"Cisco Nvidia A16 64GB 250W DW FH\/HL GPU | UCSX-GPU-A16","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cul class=\"margin-empty margin-bottom\"\u003e\n\u003cli\u003e\n\u003cb\u003eModel\u003c\/b\u003e: A100\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGPU Memory\u003c\/b\u003e: 40 GB HBM2e\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMemory ECC\u003c\/b\u003e: Y\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMemory Bandwidth\u003c\/b\u003e: 1935 GB\/sec\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMax Power Consumption\u003c\/b\u003e: 300W\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGraphic Bus \/ System Interface\u003c\/b\u003e: PCIe Gen4x16\/ NVLink bridge\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eInterconnect Bandwidth\u003c\/b\u003e: 64 GB\/sec (PCIe 4.0)\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eSlot Width\u003c\/b\u003e: DW\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGPU Height \/ Length\u003c\/b\u003e: FHFL\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eAuxiliary Cable\u003c\/b\u003e: CPU 8 pin\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eWorkload\u003c\/b\u003e: HPC\/AI\/Database Analytics\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003chr\u003e\n\u003cp\u003eNVIDIA A100 Tensor Core GPU delivers unprecedented acceleration at every scale to power the world’s highest-performing elastic data centers for AI, data analytics, and HPC. Powered by the NVIDIA Ampere Architecture, A100 is the engine of the NVIDIA data center platform. A100 provides up to 20X higher performance over the prior generation and can be partitioned into seven GPU instances to dynamically adjust to shifting demands. The A100 40GB debuts the world’s fastest memory bandwidth at over 2 terabytes per second (TB\/s) to run the largest models and datasets.\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49588340326712,"sku":"UCSX-GPU-A16","price":0.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/A16.jpg?v=1674666535"},{"product_id":"cisco-nvidia-a40-48gb-x16-pci-e-300w-dw-fh-hl-gpu-ucsx-gpu-a40","title":"Cisco Nvidia A40 48GB x16  PCI-e 300W DW FH\/HL GPU | UCSX-GPU-A40","description":"\n  \n  \u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cp\u003eThe NVIDIA A40 GPU is an evolutionary leap in performance and multi-workload capabilities from the data center, combining best-in-class professional graphics with powerful compute and AI acceleration to meet today’s design, creative, and scientific challenges. Driving the next generation of virtual workstations and server-based workloads, NVIDIA A40 brings state-of-the-art features for ray-traced rendering, simulation, virtual production, and more to professionals anytime, anywhere.\u003c\/p\u003e\n\u003chr\u003e\n  \n\u003cdiv class=\"product-section container jc-between-center is-flex-row\"\u003e\n\u003cdiv class=\"eight medium-down--one-whole-NG\"\u003e\n\u003cb\u003eNVIDIA Ampere Architecture CUDA® Cores\u003c\/b\u003e\n\u003cp\u003eDouble-speed processing for single-precision floating point (FP32) operations and improved power efficiency provide significant performance improvements for graphics and simulation workflows, such as complex 3D computer-aided design (CAD) and computer-aided engineering (CAE).\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"eight medium-down--one-whole-NG\"\u003e\n\u003cb\u003eThird-Generation NVIDIA NVLink®\u003c\/b\u003e\n\u003cp\u003eConnect two A40 GPUs together to scale from 48GB of GPU memory to 96GB. Increased GPU-to-GPU interconnect bandwidth provides a single scalable memory to accelerate graphics and compute workloads and tackle larger datasets. A new, more compact NVLink connector enables functionality in a wider range of servers.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003chr\u003e\n  \n\u003cdiv class=\"product-section container jc-between-center is-flex-row\"\u003e\n\u003cdiv class=\"eight medium-down--one-whole-NG\"\u003e\n\u003cb\u003eSecond-Generation RT Cores\u003c\/b\u003e\n\u003cp\u003eWith up to 2X the throughput over the previous generation and the ability to concurrently run ray tracing with either shading or denoising capabilities, second-generation RT Cores deliver massive speedups for workloads like photorealistic rendering of movie content, architectural design evaluations, and virtual prototyping of product designs. This technology also speeds up the rendering of ray-traced motion blur for faster results with greater visual accuracy.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"eight medium-down--one-whole-NG\"\u003e\n\u003cb\u003eVirtualization-Ready\u003c\/b\u003e\n\u003cp\u003eNext-generation improvements with NVIDIA virtual GPU (vGPU) software allow for larger, more powerful virtual workstation instances for remote users, enabling high-end remote design, AI, and compute workloads.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003chr\u003e\n  \n\u003cdiv class=\"product-section container jc-between-center is-flex-row\"\u003e\n\u003cdiv class=\"eight medium-down--one-whole-NG\"\u003e\n\u003cb\u003eThird-Generation Tensor Cores\u003c\/b\u003e\n\u003cp\u003eNew Tensor Float 32 (TF32) precision provides up to 5X the training throughput over the previous generation to accelerate AI and data science model training without requiring any code changes. Hardware support for structural sparsity doubles the throughput for inferencing. Tensor Cores also bring AI to graphics with capabilities like DLSS, AI denoising, and enhanced editing for select applications.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"eight medium-down--one-whole-NG\"\u003e\n\u003cb\u003ePCI Express Gen 4\u003c\/b\u003e\n\u003cp\u003ePCI Express Gen 4 doubles the bandwidth of PCIe Gen 3, improving data-transfer speeds from CPU memory for data-intensive tasks like AI, data science, and 3D design. Faster PCIe performance also accelerates GPU direct memory access (DMA) transfers, providing faster I\/O communication of video data between the GPU and GPUDirect® for Video-enabled devices delivering a powerful solution for live broadcast. A40 is backwards compatible with PCI Express Gen 3 for deployment flexibility.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e\n\u003chr\u003e\n  \n\u003cdiv class=\"product-section container jc-between-center is-flex-row\"\u003e\n\u003cdiv class=\"eight medium-down--one-whole-NG\"\u003e\n\u003cb\u003e48GB of GPU Memory\u003c\/b\u003e\n\u003cp\u003eUltra-fast GDDR6 memory, scalable up to 96GB with NVLink, gives data scientists, engineers, and creative professionals the large memory necessary to work with massive datasets and workloads like data science and simulation.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"eight medium-down--one-whole-NG\"\u003e\n\u003cb\u003eData Center Efficiency and Security\u003c\/b\u003e\n\u003cp\u003eFeaturing a dual-slot, power efficient design, NVIDIA A40 is up to 2X as power efficient as the previous generation that is validated with a wide range of NVIDIA-Certified systems from worldwide OEMs. The NVIDIA A40 also provides secure and measured boot with hardware root of trust capability, ensuring that firmware has not been tampered with or corrupted.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49588341408056,"sku":"UCSX-GPU-A40","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/A40.jpg?v=1674667744"},{"product_id":"cisco-nvidia-tesla-a100-80gb-dw-ucsx-gpu-a100-80","title":"Cisco Nvidia Tesla A100 80GB DW GPU | UCSX-GPU-A100-80","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003chr\u003e\n\u003cul class=\"margin-empty margin-bottom\"\u003e\n\u003cli\u003eAll GPU cards must be procured from Cisco as there is a unique SBIOS ID required by CIMC and UCSM\u003c\/li\u003e\n\u003cli\u003eNVIDIA Double Wide GPUs are supported\u003c\/li\u003e\n\u003cli\u003eThis GPU requires x16 support.\u003c\/li\u003e\n\u003cli\u003eThis GPU can be populated in Riser 1A slot 2 (x16), Riser 2A slot 5 (x16), and Riser 3C slot 7 (x16).\u003c\/li\u003e\n\u003cli\u003eEach server can support three of these GPUs.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49593013862712,"sku":"UCSC-GPU-A100-80","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/A100-pci_960867b2-d284-4a27-874f-a01ac174d9e5.jpg?v=1697063546"},{"product_id":"cisco-nvidia-tesla-a100-80gb-dw-ucsx-gpu-a100-80-d","title":"Cisco Nvidia Tesla A100 80GB DW GPU | UCSX-GPU-A100-80-D","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cul\u003e\n\u003cli\u003eAll GPU cards must be procured from Cisco as there is a unique SBIOS ID required by CIMC and UCSM\u003c\/li\u003e\n\u003cli\u003eThis GPU requires x16 support.\u003c\/li\u003e\n\u003cli\u003eThis GPU can be populated in Riser 1A slot 2 (x16), Riser 2A slot 5 (x16), and Riser 3C slot 7 (x16).\u003c\/li\u003e\n\u003cli\u003eEach server can support three of these GPUs.\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49593014026552,"sku":"UCSX-GPU-A100-80-D","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/A100-pci_960867b2-d284-4a27-874f-a01ac174d9e5.jpg?v=1697063546"},{"product_id":"cisco-nvidia-a40-48gb-x16-pci-e-300w-dw-fh-hl-gpu-ucsx-gpu-a40-d","title":"Cisco Nvidia A40 48GB x16  PCI-e 300W DW FH\/HL GPU | UCSX-GPU-A40-D","description":"\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \n\u003cdiv class=\"product-section container is-flex is-flex-wrap\"\u003e\n\u003cp\u003eThe NVIDIA A40 GPU is an evolutionary leap in performance and multi-workload capabilities from the data center, combining best-in-class professional graphics with powerful compute and AI acceleration to meet today’s design, creative, and scientific challenges. Driving the next generation of virtual workstations and server-based workloads, NVIDIA A40 brings state-of-the-art features for ray-traced rendering, simulation, virtual production, and more to professionals anytime, anywhere.\u003c\/p\u003e\n\u003chr\u003e\n\u003cdiv class=\"eight medium-down--one-whole-NG\"\u003e\n\u003cb\u003eNVIDIA Ampere Architecture CUDA® Cores\u003c\/b\u003e\n\u003cp\u003eDouble-speed processing for single-precision floating point (FP32) operations and improved power efficiency provide significant performance improvements for graphics and simulation workflows, such as complex 3D computer-aided design (CAD) and computer-aided engineering (CAE).\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"eight medium-down--one-whole-NG\"\u003e\n\u003chr class=\"is-hidden-mobile-only\"\u003e\n\u003cb\u003eThird-Generation NVIDIA NVLink®\u003c\/b\u003e\n\u003cp\u003eConnect two A40 GPUs together to scale from 48GB of GPU memory to 96GB. Increased GPU-to-GPU interconnect bandwidth provides a single scalable memory to accelerate graphics and compute workloads and tackle larger datasets. A new, more compact NVLink connector enables functionality in a wider range of servers.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003chr\u003e\n\u003cdiv class=\"eight medium-down--one-whole-NG\"\u003e\n\u003cb\u003eSecond-Generation RT Cores\u003c\/b\u003e\n\u003cp\u003eWith up to 2X the throughput over the previous generation and the ability to concurrently run ray tracing with either shading or denoising capabilities, second-generation RT Cores deliver massive speedups for workloads like photorealistic rendering of movie content, architectural design evaluations, and virtual prototyping of product designs. This technology also speeds up the rendering of ray-traced motion blur for faster results with greater visual accuracy.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"eight medium-down--one-whole-NG\"\u003e\n\u003chr class=\"is-hidden-mobile-only\"\u003e\n\u003cb\u003eVirtualization-Ready\u003c\/b\u003e\n\u003cp\u003eNext-generation improvements with NVIDIA virtual GPU (vGPU) software allow for larger, more powerful virtual workstation instances for remote users, enabling high-end remote design, AI, and compute workloads.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003chr\u003e\n\u003cdiv class=\"eight medium-down--one-whole-NG\"\u003e\n\u003cb\u003eThird-Generation Tensor Cores\u003c\/b\u003e\n\u003cp\u003eNew Tensor Float 32 (TF32) precision provides up to 5X the training throughput over the previous generation to accelerate AI and data science model training without requiring any code changes. Hardware support for structural sparsity doubles the throughput for inferencing. Tensor Cores also bring AI to graphics with capabilities like DLSS, AI denoising, and enhanced editing for select applications.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"eight medium-down--one-whole-NG\"\u003e\n\u003chr class=\"is-hidden-mobile-only\"\u003e\n\u003cb\u003ePCI Express Gen 4\u003c\/b\u003e\n\u003cp\u003ePCI Express Gen 4 doubles the bandwidth of PCIe Gen 3, improving data-transfer speeds from CPU memory for data-intensive tasks like AI, data science, and 3D design. Faster PCIe performance also accelerates GPU direct memory access (DMA) transfers, providing faster I\/O communication of video data between the GPU and GPUDirect® for Video-enabled devices delivering a powerful solution for live broadcast. A40 is backwards compatible with PCI Express Gen 3 for deployment flexibility.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003chr\u003e\n\u003cdiv class=\"eight medium-down--one-whole-NG\"\u003e\n\u003cb\u003e48GB of GPU Memory\u003c\/b\u003e\n\u003cp\u003eUltra-fast GDDR6 memory, scalable up to 96GB with NVLink, gives data scientists, engineers, and creative professionals the large memory necessary to work with massive datasets and workloads like data science and simulation.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003cdiv class=\"eight medium-down--one-whole-NG\"\u003e\n\u003chr class=\"is-hidden-mobile-only\"\u003e\n\u003cb\u003eData Center Efficiency and Security\u003c\/b\u003e\n\u003cp\u003eFeaturing a dual-slot, power efficient design, NVIDIA A40 is up to 2X as power efficient as the previous generation that is validated with a wide range of NVIDIA-Certified systems from worldwide OEMs. The NVIDIA A40 also provides secure and measured boot with hardware root of trust capability, ensuring that firmware has not been tampered with or corrupted.\u003c\/p\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49593015402808,"sku":"UCSX-GPU-A40-D","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/A40.jpg?v=1674667744"},{"product_id":"cisco-nvidia-a16-64gb-250w-dw-fh-hl-gpu-ucsx-gpu-a16-d","title":"Cisco Nvidia A16 64GB 250W DW FH\/HL GPU | UCSX-GPU-A16-D","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cul class=\"margin-empty margin-bottom\"\u003e\n\u003cli\u003e\n\u003cb\u003eModel\u003c\/b\u003e:  A16\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGPU Memory\u003c\/b\u003e:  64 GB GDDR6\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMemory ECC\u003c\/b\u003e:  Y\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMemory Bandwidth\u003c\/b\u003e:  800 GB\/sec \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMax Power Consumption\u003c\/b\u003e:  250W \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGraphic Bus \/ System Interface\u003c\/b\u003e:  PCIe Gen4x16 \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eInterconnect Bandwidth\u003c\/b\u003e:  64 GB\/sec (PCIe 4.0) \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eSlot Width\u003c\/b\u003e:  DW \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGPU Height \/ Length\u003c\/b\u003e:  FHFL \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eAuxiliary Cable\u003c\/b\u003e:  CPU 8 pin \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eWorkload\u003c\/b\u003e:  VDI\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003chr\u003e\n\u003cp\u003eTake remote work to the next level with NVIDIA A16. Combined with NVIDIA Virtual PC (vPC) or NVIDIA RTX Virtual Workstation (vWS) software, it enables virtual desktops and workstations with the power and performance to tackle any project from anywhere. Purpose-built for high-density, graphics-rich virtual desktop infrastructure (VDI) and leveraging the NVIDIA Ampere architecture, A16 provides double the user density versus the previous generation, while ensuring the best possible user experience.\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49593021301048,"sku":"UCSX-GPU-A16-D","price":0.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/A16.jpg?v=1674666535"},{"product_id":"cisco-ucs-nvidia-tesla-t4-16gb-x16-pci-e-70w-sw-hh-hl-gpu-ucsx-gpu-t4-16-d","title":"Cisco Ucs Nvidia Tesla T4 16GB 70W SW HH\/HL GPU | UCSX-GPU-T4-16-D","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cb\u003eModel\u003c\/b\u003e: T4 \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGPU Memory\u003c\/b\u003e: 16 GB GDDR6 \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMemory ECC\u003c\/b\u003e: Y \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMemory Bandwidth\u003c\/b\u003e: 300 GB\/sec \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMax Power Consumption\u003c\/b\u003e: 70W \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGraphic Bus \/ System Interface\u003c\/b\u003e: PCIe Gen3x16 \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eInterconnect Bandwidth\u003c\/b\u003e: 32 GB\/sec (PCIe 3.0) \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eSlot Width\u003c\/b\u003e: SW \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGPU Height \/ Length\u003c\/b\u003e: HHHL \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eAuxiliary Cable\u003c\/b\u003e: N\/A \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eWorkload\u003c\/b\u003e: Inferencing\/Edge\/VDI \u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49593021628728,"sku":"UCSX-GPU-T4-16-D","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/nvidia-tesla-t4_b120c7be-c8d6-41ad-9d60-1646c6670bf5.jpg?v=1676588264"},{"product_id":"cisco-ucs-m7-nvidia-tesla-t4-16gb-75w-sw-mezzanine-gpu-ucsx-gpu-t4mezz-d","title":"Cisco Ucs M7 Nvidia Tesla T4 16GB 75W SW Mezzanine GPU | UCSX-GPU-T4MEZZ-D","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cul\u003e\n\u003cli\u003e\n\u003cb\u003eModel\u003c\/b\u003e: T4\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGPU Memory\u003c\/b\u003e: 16 GB GDDR6\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMemory ECC\u003c\/b\u003e: Y\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMemory Bandwidth\u003c\/b\u003e: 300 GB\/sec\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMax Power Consumption\u003c\/b\u003e: 75W \u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGraphic Bus \/ System Interface\u003c\/b\u003e: PCIe Gen4x16\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eInterconnect Bandwidth\u003c\/b\u003e: 32 GB\/sec (PCIe 3.0)\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eSlot Width\u003c\/b\u003e: SW\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGPU Height \/ Length\u003c\/b\u003e: Mezzanine\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eAuxiliary Cable\u003c\/b\u003e: N\/A\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eWorkload\u003c\/b\u003e: Inferencing\/Edge\/VDI\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49596046934328,"sku":"UCSX-GPU-T4MEZZ-D","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/nvidia-tesla-t4_b120c7be-c8d6-41ad-9d60-1646c6670bf5.jpg?v=1676588264"},{"product_id":"cisco-nvidia-l4-70w-24gb-mezzanine-gpu-ucsx-gpu-l4-mezz","title":"Cisco Nvidia L4 70W 24GB Mezzanine GPU | UCSX-GPU-L4-MEZZ","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n  \u003cp\u003eThe NVIDIA L4 Tensor Core GPU powered by the NVIDIA Ada Lovelace architecture delivers universal, energy-efficient acceleration for video, AI, visual computing, graphics, virtualization, and more. Packaged in a low-profile form factor, L4 is a cost-effective, energy-efficient solution for high throughput and low latency in every server, from the edge to the data center to the cloud. \u003c\/p\u003e\n\n\u003cdiv class=\"table-mobile\"\u003e\n  \u003ctable\u003e\n\u003cthead\u003e\u003ctr\u003e\n\u003cth\u003eForm Factor\u003c\/th\u003e\n\u003cth\u003eL4\u003c\/th\u003e\n\u003c\/tr\u003e\u003c\/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eFP32\u003c\/td\u003e\n\u003ctd\u003e30.3 teraFLOPs\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eTF32 Tensor Core\u003c\/td\u003e\n\u003ctd\u003e120 teraFLOPS*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eFP16 Tensor Core\u003c\/td\u003e\n\u003ctd\u003e242 teraFLOPS*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eBFLOAT16 Tensor Core\u003c\/td\u003e\n\u003ctd\u003e242 teraFLOPS*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eFP8 Tensor Core\u003c\/td\u003e\n\u003ctd\u003e485 teraFLOPs*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eINT8 Tensor Core\u003c\/td\u003e\n\u003ctd\u003e485 TOPs*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eGPU memory\u003c\/td\u003e\n\u003ctd\u003e24GB\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eGPU memory bandwidth\u003c\/td\u003e\n\u003ctd\u003e300GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNVENC | NVDEC | JPEG decoders\u003c\/td\u003e\n\u003ctd\u003e2 | 4 | 4\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMax thermal design power (TDP)\u003c\/td\u003e\n\u003ctd\u003e72W\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eForm factor\u003c\/td\u003e\n\u003ctd\u003e1-slot low-profile, PCIe\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eInterconnect\u003c\/td\u003e\n\u003ctd\u003ePCIe Gen4 x16 64GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eServer options\u003c\/td\u003e\n\u003ctd\u003ePartner and NVIDIA-Certified Systems with 1–8 GPUs\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49596048638264,"sku":"UCSX-GPU-L4-MEZZ","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/L4_2cc52bb8-b20e-43ea-b9fe-70a5866d8806.jpg?v=1698789001"},{"product_id":"cisco-intel-flex-140-75w-mezzanine-gpu-ucsx-gpu-flx140mz","title":"Cisco Intel Flex 140, 75W Mezzanine GPU | UCSX-GPU-FLX140MZ","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cp\u003eThis GPU is supported on the x210c GPU front mezzanine drive cage node. This node gets installed into the x9508 Enclosure. \u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49596050637112,"sku":"UCSX-GPU-FLX140MZ","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/L4_2cc52bb8-b20e-43ea-b9fe-70a5866d8806.jpg?v=1698789001"},{"product_id":"cisco-ucs-nvidia-h100-80gb-passive-350w-dw-fh-hl-gpu-ucsx-gpu-h100-80","title":"Cisco Ucs Nvidia H100 80GB Passive 350W DW FH\/HL GPU | UCSX-GPU-H100-80","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cul class=\"margin-empty margin-bottom\"\u003e\n\u003cli\u003e\n\u003cb\u003eModel\u003c\/b\u003e: H100\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGPU Memory\u003c\/b\u003e: 80GB HBM2e\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMemory ECC\u003c\/b\u003e: Y\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMemory Bandwidth\u003c\/b\u003e: 2000 GB\/sec\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMax Power Consumption\u003c\/b\u003e: 350W\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGraphic Bus \/ System Interface\u003c\/b\u003e: PCIe Gen5x16\/ NVLink bridge\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eInterconnect Bandwidth\u003c\/b\u003e: 128 GB\/sec (PCIe 5.0)\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eSlot Width\u003c\/b\u003e: DW\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGPU Height \/ Length\u003c\/b\u003e: FHFL\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eAuxiliary Cable\u003c\/b\u003e: PCIe 16 pin\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eWorkload\u003c\/b\u003e: HPC\/AI\/Database Analytics\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003chr\u003e\n\u003cp\u003eTap into unprecedented performance, scalability, and security for every workload with the NVIDIA H100 Tensor Core GPU. With NVIDIA \u003csup\u003e®\u003c\/sup\u003e NVLink\u003csup\u003e®\u003c\/sup\u003e Switch System, up to 256 H100s can be connected to accelerate exascale workloads, along with a dedicated Transformer Engine to solve trillion-parameter language models. H100’s combined technology innovations can speed up large language models by an incredible 30X over the previous generation to deliver industry-leading conversational AI.\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49596054307128,"sku":null,"price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/H100-pci.jpg?v=1674668860"},{"product_id":"cisco-nvidia-l4-tensor-core-gpu-72w-24gb-pcie-accelerator-ucsx-gpu-l4","title":"Cisco Nvidia L4 Tensor Core 72W 24GB GPU | UCSX-GPU-L4","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cp\u003eThe NVIDIA L4 Tensor Core GPU powered by the NVIDIA Ada Lovelace architecture delivers universal, energy-efficient acceleration for video, AI, visual computing, graphics, virtualization, and more. Packaged in a low-profile form factor, L4 is a cost-effective, energy-efficient solution for high throughput and low latency in every server, from the edge to the data center to the cloud. \u003c\/p\u003e\n\n\u003cdiv class=\"table-mobile\"\u003e\n  \u003ctable\u003e\n\u003cthead\u003e\u003ctr\u003e\n\u003cth\u003eForm Factor\u003c\/th\u003e\n\u003cth\u003eL4\u003c\/th\u003e\n\u003c\/tr\u003e\u003c\/thead\u003e\n\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eFP32\u003c\/td\u003e\n\u003ctd\u003e30.3 teraFLOPs\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eTF32 Tensor Core\u003c\/td\u003e\n\u003ctd\u003e120 teraFLOPS*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eFP16 Tensor Core\u003c\/td\u003e\n\u003ctd\u003e242 teraFLOPS*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eBFLOAT16 Tensor Core\u003c\/td\u003e\n\u003ctd\u003e242 teraFLOPS*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eFP8 Tensor Core\u003c\/td\u003e\n\u003ctd\u003e485 teraFLOPs*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eINT8 Tensor Core\u003c\/td\u003e\n\u003ctd\u003e485 TOPs*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eGPU memory\u003c\/td\u003e\n\u003ctd\u003e24GB\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eGPU memory bandwidth\u003c\/td\u003e\n\u003ctd\u003e300GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNVENC | NVDEC | JPEG decoders\u003c\/td\u003e\n\u003ctd\u003e2 | 4 | 4\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMax thermal design power (TDP)\u003c\/td\u003e\n\u003ctd\u003e72W\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eForm factor\u003c\/td\u003e\n\u003ctd\u003e1-slot low-profile, PCIe\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eInterconnect\u003c\/td\u003e\n\u003ctd\u003ePCIe Gen4 x16 64GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eServer options\u003c\/td\u003e\n\u003ctd\u003ePartner and NVIDIA-Certified Systems with 1–8 GPUs\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\n\u003c\/table\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49596055683384,"sku":"UCSX-GPU-L4","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/L4_2cc52bb8-b20e-43ea-b9fe-70a5866d8806.jpg?v=1698789001"},{"product_id":"cisco-ucs-nvidia-l40-48gb-dw-passive-cooling-pcie-gpu-ucsx-gpu-l40","title":"Cisco UCS Nvidia L40 48GB DW Passive Cooling GPU | UCSX-GPU-L40","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cdiv class=\"table-mobile\"\u003e\u003ctable\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eGPU Architecture\u003c\/td\u003e\n\u003ctd\u003eNVIDIA Ada Lovelace Architecture\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eGPU Memory Bandwidth\u003c\/td\u003e\n\u003ctd\u003e864GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eGPU Memory\u003c\/td\u003e\n\u003ctd\u003e48 GB GDDR6 with ECC\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDisplay Connectors\u003c\/td\u003e\n\u003ctd\u003e4 x DP 1.4a\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMax Power Consumption\u003c\/td\u003e\n\u003ctd\u003e300W\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eForm Factor\u003c\/td\u003e\n\u003ctd\u003e4.4\" (H) x 10.5\" (L) Dual Slot\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eThermal\u003c\/td\u003e\n\u003ctd\u003ePassive\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003evGPU Software Support\u003c\/td\u003e\n\u003ctd\u003eNVIDIA vPC\/vApps, NVIDIA RTX Virtual Workstation (vWS)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003evGPU Profiles Supported\u003c\/td\u003e\n\u003ctd\u003e\u003ca href=\"https:\/\/www.nvidia.com\/content\/dam\/en-zz\/Solutions\/design-visualization\/solutions\/resources\/documents1\/Virtual-GPU-Packaging-and-Licensing-Guide.pdf\" target=\"_blank\"\u003eSee the Virtual GPU Licensing Guide\u003c\/a\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNVENC | NVDEC\u003c\/td\u003e\n\u003ctd\u003e3x | 3x (Includes AV1 Encode \u0026amp; Decode)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eSecure Boot with Root of Trust\u003c\/td\u003e\n\u003ctd\u003eYes\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNEBS Ready\u003c\/td\u003e\n\u003ctd\u003eYes \/ Level 3\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePower Connector\u003c\/td\u003e\n\u003ctd\u003e1x PCIe CEM5 16-pin\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\u003c\/div\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49596057092408,"sku":"UCSX-GPU-L40","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/L40S.jpg?v=1698789288"},{"product_id":"ucsx-gpu-l40s","title":"Cisco Nvidia L40S 350W DW GPU | UCSX-GPU-L40S","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003cbr\u003e\u003cdiv class=\"table-mobile\"\u003e\u003ctable\u003e\u003ctbody\u003e\n\u003ctr\u003e\n\u003ctd\u003eGPU Architecture\u003c\/td\u003e\n\u003ctd\u003eNVIDIA Ada Lovelace architecture\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eGPU Memory\u003c\/td\u003e\n\u003ctd\u003e48GB GDDR6 with ECC\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMemory Bandwidth\u003c\/td\u003e\n\u003ctd\u003e864GB\/s\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eInterconnect Interface\u003c\/td\u003e\n\u003ctd\u003ePCIe Gen4 x16: 64GB\/s bidirectional\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNVIDIA Ada Lovelace Architecture-Based CUDA® Cores\u003c\/td\u003e\n\u003ctd\u003e18,176\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNVIDIA Third-Generation RT Cores\u003c\/td\u003e\n\u003ctd\u003e142\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNVIDIA Fourth-Generation Tensor Cores\u003c\/td\u003e\n\u003ctd\u003e568\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eRT Core Performance TFLOPS\u003c\/td\u003e\n\u003ctd\u003e212 \u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eFP32 TFLOPS\u003c\/td\u003e\n\u003ctd\u003e91.6\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eTF32 Tensor Core TFLOPS\u003c\/td\u003e\n\u003ctd\u003e183 I 366*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eBFLOAT16 Tensor Core TFLOPS\u003c\/td\u003e\n\u003ctd\u003e362.05 I 733*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eFP16 Tensor Core\u003c\/td\u003e\n\u003ctd\u003e362.05 I 733*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eFP8 Tensor Core\u003c\/td\u003e\n\u003ctd\u003e733 I 1,466*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePeak INT8 Tensor TOPS\u003cbr\u003e Peak INT4 Tensor TOPS\u003c\/td\u003e\n\u003ctd\u003e733 I 1,466*\u003cbr\u003e 733 I 1,466*\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eForm Factor\u003c\/td\u003e\n\u003ctd\u003e4.4\" (H) x 10.5\" (L), dual slot\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eDisplay Ports\u003c\/td\u003e\n\u003ctd\u003e4x DisplayPort 1.4a\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMax Power Consumption\u003c\/td\u003e\n\u003ctd\u003e350W\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003ePower Connector\u003c\/td\u003e\n\u003ctd\u003e16-pin\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eThermal\u003c\/td\u003e\n\u003ctd\u003ePassive\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eVirtual GPU (vGPU) Software Support\u003c\/td\u003e\n\u003ctd\u003eYes\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003evGPU Profiles Supported\u003c\/td\u003e\n\u003ctd\u003e\u003cbr\u003e\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNVENC I NVDEC\u003c\/td\u003e\n\u003ctd\u003e3x l 3x (includes AV1 encode and decode)\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eSecure Boot With Root of Trust\u003c\/td\u003e\n\u003ctd\u003eYes\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNEBS Ready\u003c\/td\u003e\n\u003ctd\u003eLevel 3\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eMulti-Instance GPU (MIG) Support\u003c\/td\u003e\n\u003ctd\u003eNo\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003ctr\u003e\n\u003ctd\u003eNVIDIA® NVLink® Support\u003c\/td\u003e\n\u003ctd\u003eNo\u003c\/td\u003e\n\u003c\/tr\u003e\n\u003c\/tbody\u003e\u003c\/table\u003e\u003c\/div\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49596058927416,"sku":"UCSX-GPU-L40S","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/L40S_02bc77b3-f3e9-4011-847a-42c46b388641.jpg?v=1698789311"},{"product_id":"cisco-intel-flex-140-75w-sw-gpu-ucsx-gpu-flex140","title":"Cisco Intel Flex 140 75W SW GPU | UCSX-GPU-FLEX140","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cul class=\"margin-empty\"\u003e\n\u003cli\u003e\n\u003cb\u003eManufacturer\u003c\/b\u003e: Intel\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eModle\u003c\/b\u003e: Flex 140\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eWattage\u003c\/b\u003e: 75w\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eForm Factor\u003c\/b\u003e: HHHL Single Wide\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003chr\u003e\n\u003cp\u003eAll GPU cards must be procured from Cisco as there is a unique SBIOS IDrequired by CIMC and UCSM\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49596059844920,"sku":"UCSX-GPU-FLEX140","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/L4_2cc52bb8-b20e-43ea-b9fe-70a5866d8806.jpg?v=1698789001"},{"product_id":"cisco-intel-flex-170-150w-sw-gpu-ucsx-gpu-flex170","title":"Cisco Intel Flex 170 150W SW GPU | UCSX-GPU-FLEX170","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cul class=\"margin-empty margin-bottom\"\u003e\n\u003cli\u003e\n\u003cb\u003eManufacturer\u003c\/b\u003e: Intel\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eModle\u003c\/b\u003e: Flex 170\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eWattage\u003c\/b\u003e: 150w\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eForm Factor\u003c\/b\u003e: HHHL Single Wide\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003chr\u003e\n\u003cp\u003eAll GPU cards must be procured from Cisco as there is a unique SBIOS ID required by CIMC and UCSM\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49596063285560,"sku":"UCSX-GPU-FLEX170","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/L4_2cc52bb8-b20e-43ea-b9fe-70a5866d8806.jpg?v=1698789001"},{"product_id":"cisco-nvidia-h100-nvl-94gb-x16-pci-e-350w-passive-dw-fh-gpu-ucsx-gpu-h100-nvl","title":"Cisco Nvidia H100 Nvl 94GB x16  PCI-e 350W Passive DW FH GPU | UCSX-GPU-H100-NVL","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cul class=\"margin-empty margin-bottom\"\u003e\n\u003cli\u003e\n\u003cb\u003eModel\u003c\/b\u003e: H100\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGPU Memory\u003c\/b\u003e: 96GB\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMemory Bandwidth\u003c\/b\u003e: 3.9TB\/s\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eMax Power Consumption\u003c\/b\u003e: 350-400W (configurable)\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eGraphic Bus \/ System Interface\u003c\/b\u003e: PCIe Gen5x16\/ NVIDIA NVLink: 600GB\/s\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eInterconnect Bandwidth\u003c\/b\u003e: 128 GB\/sec (PCIe 5.0)\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eSlot Width\u003c\/b\u003e: DW\u003c\/li\u003e\n\u003cli\u003e\n\u003cb\u003eNVIDIA AI Enterprise\u003c\/b\u003e: Included\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003chr\u003e\n\u003cb\u003eSupercharge Large Language Model Inference With H100 NVL\u003c\/b\u003e\n\u003cp\u003eFor LLMs up to 70 billion parameters (Llama 2 70B), the PCIe-based NVIDIA H100 NVL with NVLink bridge utilizes Transformer Engine, NVLink, and 188GB HBM3 memory to provide optimum performance and easy scaling across any data center, bringing LLMs to the mainstream. Servers equipped with H100 NVL GPUs increase Llama 2 70B performance up to 5X over NVIDIA A100 systems while maintaining low latency in power-constrained data center environments.\u003c\/p\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49596066791736,"sku":"UCSX-GPU-H100-NVL","price":0.0,"currency_code":"USD","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/H100-pci.jpg?v=1674668860"},{"product_id":"cisco-nvidia-t4-16gb-low-profile-single-width-gpu-hx-gpu-t4-16","title":"Cisco Nvidia T4 16GB Low Profile Single-Width GPU | HX-GPU-T4-16","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cp\u003eThe NVIDIA \u003csup\u003e®\u003c\/sup\u003e T4 GPU accelerates diverse cloud workloads, including high-performance computing, deep learning training and inference, machine learning, data analytics, and graphics. Based on the new NVIDIA Turing \u003csup\u003e™\u003c\/sup\u003e architecture and packaged in an energy-efficient 70-watt, small PCIe form factor, T4 is optimized for mainstream computing environments and features multi-precision Turing Tensor Cores and new RT Cores. Combined with accelerated containerized software stacks from NGC, T4 delivers revolutionary performance at scale.\u003c\/p\u003e\n\u003chr\u003e\n\u003cb\u003eSPECIFICATIONS\u003c\/b\u003e\u003cul\u003e\n\u003cli\u003eGPU Architecture NVIDIA Turing \u003c\/li\u003e\n\u003cli\u003eNVIDIA Turing Tensor Cores 320 \u003c\/li\u003e\n\u003cli\u003eNVIDIA CUDA ® Cores 2,560 \u003c\/li\u003e\n\u003cli\u003eSingle-Precision 8.1 TFLOPS \u003c\/li\u003e\n\u003cli\u003eMixed-Precision (FP16\/FP32) 65 TFLOPS \u003c\/li\u003e\n\u003cli\u003eINT8 130 TOPS \u003c\/li\u003e\n\u003cli\u003eINT4 260 TOPS \u003c\/li\u003e\n\u003cli\u003eGPU Memory 16 GB GDDR6 | 300 GB\/sec\u003c\/li\u003e\n\u003cli\u003eECC Yes \u003c\/li\u003e\n\u003cli\u003eInterconnect \u003c\/li\u003e\n\u003cli\u003eBandwidth 32 GB\/sec \u003c\/li\u003e\n\u003cli\u003eSystem Interface x16 PCIe Gen3 \u003c\/li\u003e\n\u003cli\u003eForm Factor Low-Profile PCIe \u003c\/li\u003e\n\u003cli\u003eThermal Solution Passive \u003c\/li\u003e\n\u003cli\u003eCompute APIs CUDA, NVIDIA TensorRT ™ , ONNX \u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49601761083704,"sku":"HX-GPU-T4-16","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/UCSC-GPU-T4-16.jpg?v=1664912769"},{"product_id":"nvidia-quadro-rtx-6000-passive-250w-tgp-24gb-hx-gpu-rtx6000","title":"Cisco Nvidia Quadro RTX 6000 250W 24GB DW Passive GPU | HX-GPU-RTX6000","description":"\u003cdiv class=\"product-section container jc-between-center is-flex-row\"\u003e\n   \u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \u003chr\u003e\n        \u003cdiv class=\"eight medium-down--one-whole-NG \"\u003e\n         \n    \u003cul\u003e\n      \u003cli\u003eRTX 6000 PASSIVE\u003c\/li\u003e\n      \u003cli\u003eDouble Wide\u003c\/li\u003e\n      \u003cli\u003ePCIe 3.0x16\u003c\/li\u003e\n      \u003cli\u003e250W\u003c\/li\u003e\n      \u003cli\u003e24GB\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49615539634488,"sku":"HX-GPU-RTX6000","price":0.0,"currency_code":"USD","in_stock":true}]},{"product_id":"cisco-nvidia-quadro-rtx-8000-passive-250w-tgp-48gb-hx-gpu-rtx8000","title":"Cisco Nvidia Quadro RTX 8000 250W 48GB DW Passive GPU | HX-GPU-RTX8000","description":"\u003cdiv class=\"product-default-container\"\u003e\n    \u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \n    \u003cul\u003e\n        \u003cli\u003eNvidia Quadro RTX 8000 PASSIVE\u003c\/li\u003e\n      \u003cli\u003e250W\u003c\/li\u003e\n      \u003cli\u003e48GB\u003c\/li\u003e\n      \u003cli\u003eDouble Wide\u003c\/li\u003e\n    \u003c\/ul\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49615546220856,"sku":"HX-GPU-RTX8000","price":0.0,"currency_code":"USD","in_stock":true}]},{"product_id":"cisco-nvidia-m10-hx-gpu-m10","title":"Cisco Nvidia M10 | HX-GPU-M10","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cp\u003eThe NVIDIA \u003csup\u003e®\u003c\/sup\u003e M10 GPU works with NVIDIA GRID \u003csup\u003e® \u003c\/sup\u003e software to deliver the industry's highest user density for virtualized desktops and applications. It supports up to 32 users per board (1GB profile), up to 96 users per server, giving businesses the power to deliver great experiences to all of their employees at an affordable cost.\u003cbr\u003e\u003c\/p\u003e\n\u003cul\u003e\n\u003cli\u003eFour NVIDIA Maxwell\u003csup\u003e™\u003c\/sup\u003e GPUs\u003c\/li\u003e\n\u003cli\u003eUp to 32 users per board\u003c\/li\u003e\n\u003cli\u003e2560 NVIDIA CUDA\u003csup\u003e®\u003c\/sup\u003e cores (640 per GPU)\u003c\/li\u003e\n\u003cli\u003e32 GB of GDDR5 memory (8 per GPU)\u003c\/li\u003e\n\u003cli\u003e28 H.264 1080p30 streams\u003c\/li\u003e\n\u003cli\u003eECC protection for increased reliability\u003c\/li\u003e\n\u003cli\u003eServer optimization to deliver the best throughput in the data center\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49615547826488,"sku":"HX-GPU-M10","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/products\/UCSC-GPU-M10.jpg?v=1664911332"},{"product_id":"cisco-nvidia-tesla-a10-passive-150w-24gb-hx-gpu-a10","title":"Cisco Nvidia Tesla A10, Passive, 150W, 24GB GPU | HX-GPU-A10","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e\n\u003cul\u003e\n\u003cli\u003eAll GPU cards must be procured from Cisco as there is a unique SBIOS ID required by CIMC and UCSM\u003c\/li\u003e\n\u003cli\u003eSlots 4, 5, and 6 on riser card 2A accommodate single-wide GPUs\u003c\/li\u003e\n\u003cli\u003eSingle-wide\u003c\/li\u003e\n\u003cli\u003e150W\u003c\/li\u003e\n\u003cli\u003e24GB\u003c\/li\u003e\n\u003cli\u003eM6 Riser 2 (Gen 4)\u003c\/li\u003e\n\u003c\/ul\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49620637221176,"sku":"HX-GPU-A10","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/A10_869b0362-1287-445a-9ac8-3769c9d4ea7d.jpg?v=1697062376"},{"product_id":"cisco-nvidia-tesla-a100-80gb-dw-gpu-hx-gpu-a100-80","title":"Cisco Nvidia Tesla A100 80Gb, DW GPU | HX-GPU-A100-80","description":"\u003cdiv class=\"product-default-container\"\u003e\n\u003cdiv class=\"hfour\"\u003eQuick Specs\u003c\/div\u003e \n  \u003cp\u003eAll GPU cards must be procured from Cisco as there is a unique SBIOS ID required by CIMC and UCSM\u003c\/p\u003e\n\n\n    \u003cul class=\"margin-empty\"\u003e\n      \u003cli\u003eThis GPU requires x16 support.\u003c\/li\u003e\n      \u003cli\u003eThis GPU can be populated in Riser 1A slot 2 (x16), Riser 2A slot 5 (x16), and Riser 3C slot 7 (x16).\u003c\/li\u003e\n      \u003cli\u003eEach server can support three of these GPUs.\u003c\/li\u003e\n    \u003c\/ul\u003e\n\u003c\/div\u003e","brand":"Cisco","offers":[{"title":"Default Title","offer_id":49620640530744,"sku":"HX-GPU-A100-80","price":0.0,"currency_code":"USD","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0065\/1906\/2613\/files\/A100-pci_960867b2-d284-4a27-874f-a01ac174d9e5.jpg?v=1697063546"}],"url":"https:\/\/expresscomputersystems.com\/collections\/cisco-gpus\/100-500.oembed","provider":"Express Computer Systems","version":"1.0","type":"link"}