
NVIDIA® GPUs
The world's most electrifying accelerators

FP64 Workstation GPUs
NVIDIA A800 40GB Active
The NVIDIA A800 40GB Active GPU accelerates data science, AI, and HPC workflows with 432 third-generation Tensor Cores to maximize AI performance and ultra-fast and efficient inference capabilities. With third-generation NVIDIA NVLink technology, A800 40GB Active offers scalable performance for heavy AI workloads, doubling the effective memory footprint and enabling GPU-to-GPU data transfers up to 400 GB/s of bidirectional bandwidth.
Visualization GPUs
NVIDIA RTX 4000 Ada Generation
The NVIDIA RTX™ 4000 Ada Generation is the most powerful single-slot GPU for professionals, providing massive breakthroughs in speed and power efficiency to tackle demanding creative, design, and engineering workflows from the desktop. Harnessing the latest-generation RT Cores, Tensor Cores, and CUDA® cores alongside 20GB of graphics memory, RTX 4000 empowers professionals to create intricate product engineering, visionary cityscapes, and immersive entertainment.
NVIDIA RTX 5000 Ada Generation
The NVIDIA RTX™ 5000 Ada Generation GPU, powered by the NVIDIA Ada Lovelace architecture, unlocks breakthroughs in generative AI and delivers the performance required to meet the challenges of today’s professional workflows. With 100 third-generation RT Cores, 400 fourth-generation Tensor Cores, 12,800 CUDA® cores, and 32GB of graphics memory, the RTX 5000 excels in rendering, AI, graphics, and compute workload performance.
NVIDIA RTX A5000
NVIDIA Ampere architecture brings the power of real-time ray tracing, AI, and advanced graphics to millions of designers, artists, scientists, and researchers. The NVIDIA RTX™ A5000 based on Ampere architecture perfectly balances power, performance, and memory to spearhead the future of innovation from your desktop.
Connect two RTX A5000s for 48 GB of combined GPU memory with NVIDIA NVLink, unlocking the ability to work with larger models, renders and scenes, tackle memory-intensive tasks like natural language processing, and run higher-fidelity simulations to enhance your product development process.
NVIDIA RTX 4500 Ada Generation
The NVIDIA RTX™ 4500 Ada Generation is designed for professionals to tackle demanding creative, design, engineering, and scientific work from the desktop. Combining the latest generation of RT Cores, Tensor Cores, and CUDA® cores, alongside a generous 24GB of graphics memory, RTX 4500 unleashes powerful performance and efficiency for seamless productivity.
NVIDIA RTX A4000
The NVIDIA RTX™ A4000 built on the NVIDIA Ampere architecture is the most powerful single-slot GPU for professionals, delivering real-time ray tracing, AI-accelerated compute, and high-performance graphics performance to your desktop. You can engineer next-generation products, design cityscapes of the future, and create immersive entertainment experiences of tomorrow, today, from your desktop workstation.
NVIDIA RTX A6000
Built on the NVIDIA Ampere architecture, the RTX™ A6000 combines 84 second-generation RT Cores, 336 third-generation Tensor Cores, and 10,752 CUDA cores with 48 GB of graphics memory. Connect two RTX A6000s with NVIDIA NVLink for 96 GB of combined GPU memory, engineer amazing products, design state-of-the art buildings, drive scientific breakthroughs, and create immersive entertainment.
Data Center GPUs
NVIDIA H100
NVIDIA H100 Tensor Core GPU accelerates exascale scale workloads with a dedicated Transformer Engine for trillion parameter language models. For small jobs, H100 can be partitioned down to right-sized Multi-Instance GPU (MIG) partitions. The NVIDIA™ Hopper architecture with the Transformer Engine, accelerates in an order of magnitude speedup over the prior generation.
NVIDIA A2
The NVIDIA A2 Tensor Core GPU provides entry-level inference with low power (40-60 watt), a small footprint (low profile PCIe Gen4), and high performance for intelligent video analytics (IVA) or NVIDIA® AI at the edge. Servers accelerated with A2 GPUs deliver up to 20X higher inference performance versus CPUs and 1.3x more efficient IVA deployments — all at an entry-level price point.
NVIDIA A10
Built on the latest NVIDIA Ampere architecture, the NVIDIA A10 Tensor Core GPU combines second-generation RT Cores, third-generation Tensor Cores, and new streaming microprocessors with 24 gigabytes (GB) of GDDR6 memory – all in a 150W power envelope – for versatile graphics, rendering, AI, and compute performance.
NVIDIA L40S
The NVIDIA L40S GPU, based on the Ada Lovelace architecture, is the most powerful universal GPU for the data center, delivering breakthrough multi-workload acceleration for large language model (LLM) inference and training, graphics, and video applications. As the premier platform for multi-modal generative AI, the L40S GPU provides end-to-end acceleration for inference, training, graphics, and video workflows to power the next generation of AI-enabled audio, speech, 2D, video, and 3D applications.
NVIDIA L4
L4 is optimized for video and inference at scale for a broad range of AI applications, including recommendations, voice-based AI avatar assistants, generative AI, visual search, and contact center automation. Servers equipped with L4 enable up to 120X higher AI Video performance over CPU solutions, while providing 2.7X more generative AI performance, and over 4X more graphics performance versus the previous generation.
NVIDIA A40
Built on the NVIDIA Ampere architecture, the A40 combines the latest generation RT Cores, Tensor Cores, and CUDA Cores with 48GB of graphics memory for unprecedented graphics in advanced technologies such as real-time ray tracing, AI, compute, simulation, and VR are common across industries.
NVIDIA A16
Take remote work to the next level with NVIDIA A16, the ideal GPU for high-density, graphics rich VDI. NVIDIA A16 has 4x the encoder throughput versus NVIDIA T4 to provide the best user experience on a single board. Based on the latest NVIDIA Ampere architecture, A16 is purpose-built to achieve the highest user density, with up to 64 concurrent users per board in a dual slot form factor.