{"product_id":"pny-rtx-pro-6000-blackwell-gen-96gb-gddr7-workstation-graphics-card-vcnrtxpro6000-pb-399369","title":"PNY RTX Pro 6000 Blackwell Gen 96GB GDDR7 Workstation Graphics Card VCNRTXPRO6000-PB","description":"\u003ch2\u003ePNY NVIDIA RTX PRO 6000 Blackwell Workstation Edition 96GB GDDR7 Graphics Card\u003c\/h2\u003e\n\n\u003cp\u003eThe PNY NVIDIA RTX PRO 6000 Blackwell Workstation Edition is a professional desktop graphics card designed for demanding artificial intelligence, data science, engineering, visualisation, rendering and media-production workflows. It combines the NVIDIA Blackwell architecture with 96GB of ECC-equipped GDDR7 memory, providing substantial local capacity for complex models, detailed datasets and memory-intensive professional applications.\u003c\/p\u003e\n\n\u003ch3\u003eNVIDIA Blackwell Architecture\u003c\/h3\u003e\n\n\u003cp\u003eThe Blackwell architecture incorporates enhanced streaming multiprocessors, fifth-generation Tensor Cores and fourth-generation RT Cores. Its 24,064 CUDA cores support parallel graphics and compute workloads, while dedicated Tensor and ray-tracing hardware accelerates compatible AI, rendering, simulation and visualisation applications.\u003c\/p\u003e\n\n\u003ch3\u003e96GB of GDDR7 ECC Memory\u003c\/h3\u003e\n\n\u003cp\u003eA large 96GB GDDR7 memory pool allows the card to accommodate complex 3D scenes, large engineering assemblies, high-resolution media projects and sizeable local AI models. Error-correcting code helps identify and correct certain memory errors, supporting data integrity during long-running professional workloads.\u003c\/p\u003e\n\n\u003ch3\u003eHigh-Bandwidth Professional Computing\u003c\/h3\u003e\n\n\u003cp\u003eThe 512-bit memory interface delivers up to 1,792GB\/s of memory bandwidth, while the PCI Express 5.0 x16 interface provides a high-bandwidth connection to compatible workstation platforms. The GPU offers up to 4,000 theoretical AI TOPS with FP4 sparsity and approximately 125 TFLOPS of peak single-precision performance.\u003c\/p\u003e\n\n\u003ch3\u003eAdvanced AI Acceleration\u003c\/h3\u003e\n\n\u003cp\u003eFifth-generation Tensor Cores add support for FP4 precision and are designed to accelerate compatible generative AI, machine-learning and neural-rendering workloads. The card’s large local memory capacity can help professionals develop, fine-tune and run supported AI models without moving every workload to a remote service.\u003c\/p\u003e\n\n\u003ch3\u003eProfessional Ray-Traced Graphics\u003c\/h3\u003e\n\n\u003cp\u003eFourth-generation RT Cores accelerate hardware-based ray tracing for supported design, animation, architectural and visual-effects applications. Technologies including RTX Neural Shaders, RTX Mega Geometry and DLSS 4 can further improve supported real-time graphics and rendering workflows.\u003c\/p\u003e\n\n\u003ch3\u003eFour DisplayPort 2.1b Outputs\u003c\/h3\u003e\n\n\u003cp\u003eFour DisplayPort 2.1b connections support professional multi-display installations and high-resolution monitors. Supported configurations include up to four 4096 × 2160 displays at 120Hz, four 5120 × 2880 displays at 60Hz or two 7680 × 4320 displays at 60Hz, subject to display and cable capabilities.\u003c\/p\u003e\n\n\u003ch3\u003eProfessional Video Engines\u003c\/h3\u003e\n\n\u003cp\u003eFour ninth-generation NVIDIA NVENC encoders and four sixth-generation NVDEC decoders accelerate supported video-production and broadcast workflows. The updated engines add 4:2:2 H.264 and HEVC support, alongside improved HEVC and AV1 encoding capabilities.\u003c\/p\u003e\n\n\u003ch3\u003eMulti-Instance GPU Support\u003c\/h3\u003e\n\n\u003cp\u003eMulti-Instance GPU technology can divide the GPU into up to four isolated instances for compatible workflows. Supported configurations include four 24GB instances, two 48GB instances or one 96GB instance, helping organisations allocate GPU resources between suitable local users or applications.\u003c\/p\u003e\n\n\u003ch3\u003eWorkstation-Class Design\u003c\/h3\u003e\n\n\u003cp\u003eThe dual-slot, extended-height card uses a double-flow-through cooling system and has a maximum board power of 600W. Installation requires adequate chassis clearance, cooling and a compatible power supply with the necessary capacity and PCIe CEM5 16-pin connection.\u003c\/p\u003e\n\n\u003ch3\u003eKey Features:\u003c\/h3\u003e\n\n\u003cul\u003e\n\t\u003cli\u003eNVIDIA Blackwell architecture with 24,064 CUDA cores.\u003c\/li\u003e\n\t\u003cli\u003e96GB of GDDR7 memory with error-correcting code.\u003c\/li\u003e\n\t\u003cli\u003eFifth-generation Tensor Cores for supported professional AI workloads.\u003c\/li\u003e\n\t\u003cli\u003eFourth-generation RT Cores for accelerated ray-traced graphics.\u003c\/li\u003e\n\t\u003cli\u003eFour DisplayPort 2.1b outputs for high-resolution multi-display systems.\u003c\/li\u003e\n\t\u003cli\u003eFour ninth-generation NVENC and four sixth-generation NVDEC engines.\u003c\/li\u003e\n\t\u003cli\u003ePCI Express 5.0 x16 interface with a 600W maximum board power.\u003c\/li\u003e\n\u003c\/ul\u003e\n\n\u003ch3\u003eTechnical Specifications:\u003c\/h3\u003e\n\n\u003ctable border=\"1\" cellpadding=\"8\" cellspacing=\"0\" width=\"100%\"\u003e\n\t\u003ctbody\u003e\n\t\t\u003ctr bgcolor=\"#444444\"\u003e\n\t\t\t\u003cth width=\"38%\"\u003e\u003cfont color=\"#ffffff\"\u003eSpecification\u003c\/font\u003e\u003c\/th\u003e\n\t\t\t\u003cth\u003e\u003cfont color=\"#ffffff\"\u003eDetails\u003c\/font\u003e\u003c\/th\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr bgcolor=\"#f2f2f2\"\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eProduct\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003ePNY NVIDIA RTX PRO 6000 Blackwell Workstation Edition\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eManufacturer Part Number\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003eVCNRTXPRO6000-PB\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr bgcolor=\"#f2f2f2\"\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eProduct Type\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003eProfessional workstation graphics card\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eGPU Architecture\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003eNVIDIA Blackwell\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr bgcolor=\"#f2f2f2\"\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eCUDA Cores\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003e24,064\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eTensor Cores\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003e752 fifth-generation Tensor Cores\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr bgcolor=\"#f2f2f2\"\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eRay Tracing Cores\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003e188 fourth-generation RT Cores\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eAI Performance\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003eUp to 4,000 AI TOPS with theoretical FP4 sparsity\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr bgcolor=\"#f2f2f2\"\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eSingle-Precision Performance\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003eUp to 125 TFLOPS\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eGPU Memory\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003e96GB GDDR7 with ECC\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr bgcolor=\"#f2f2f2\"\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eMemory Interface\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003e512-bit\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eMemory Bandwidth\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003e1,792GB\/s\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr bgcolor=\"#f2f2f2\"\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eSystem Interface\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003ePCI Express 5.0 x16\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eDisplay Outputs\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003e4 × DisplayPort 2.1b\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr bgcolor=\"#f2f2f2\"\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eMaximum Displays\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003eFour simultaneous displays\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eSupported Display Configurations\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003eUp to 4 × 4096 × 2160 at 120Hz, 4 × 5120 × 2880 at 60Hz or 2 × 7680 × 4320 at 60Hz\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr bgcolor=\"#f2f2f2\"\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eVideo Encoding\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003e4 × ninth-generation NVIDIA NVENC engines\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eVideo Decoding\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003e4 × sixth-generation NVIDIA NVDEC engines\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr bgcolor=\"#f2f2f2\"\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eMIG Support\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003eUp to 4 × 24GB, 2 × 48GB or 1 × 96GB instance\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eGraphics APIs\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003eDirectX 12, Shader Model 6.6, OpenGL 4.6 and Vulkan 1.3\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr bgcolor=\"#f2f2f2\"\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eCompute APIs\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003eCUDA 12.8, OpenCL 3.0 and DirectCompute\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eMaximum Board Power\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003e600W\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr bgcolor=\"#f2f2f2\"\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003ePower Connector\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003e1 × PCIe CEM5 16-pin\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eCooling\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003eActive double-flow-through thermal solution\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr bgcolor=\"#f2f2f2\"\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eForm Factor\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003eDual-slot, extended-height card\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003eDimensions\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003eApproximately 305 × 137mm\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\t\u003ctr bgcolor=\"#f2f2f2\"\u003e\n\t\t\t\u003ctd\u003e\u003cstrong\u003ePackage Contents\u003c\/strong\u003e\u003c\/td\u003e\n\t\t\t\u003ctd\u003ePNY NVIDIA RTX PRO 6000 graphics card, quick-start guide and dual 8-pin to CEM5 16-pin power cable\u003c\/td\u003e\n\t\t\u003c\/tr\u003e\n\t\u003c\/tbody\u003e\n\u003c\/table\u003e\n\n\u003cp\u003eEquip a compatible professional workstation for demanding AI, visualisation, engineering and content-production workloads with the PNY NVIDIA RTX PRO 6000 Blackwell, and add it to your cart today.\u003c\/p\u003e\n","brand":"FirstShop","offers":[{"title":"Default Title","offer_id":53234620563823,"sku":"VCNRTXPRO6000-PB","price":315579.0,"currency_code":"ZAR","in_stock":false}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0457\/5893\/9300\/files\/vcnrtxpro6000-pb-graphics-cards-1250770554.jpg?v=1784796578","url":"https:\/\/www.firstshop.co.za\/products\/pny-rtx-pro-6000-blackwell-gen-96gb-gddr7-workstation-graphics-card-vcnrtxpro6000-pb-399369","provider":"FirstShop","version":"1.0","type":"link"}