https://www.nvidia.com/en-gb/data-center/h200/

NVIDIA Home Menu icon Menu icon Close icon Close icon Close icon 
Accordion is closed, click to open. Accordion is closed, click to
open. Accordion is open, click to close. Click to expand Click to
expand Click to expand menu. Click to collapse menu. Click to
collapse menu. Click to collapse menu. Click to see cart items Click
to search
Skip to main content
 
( ) ( ) ( ) ( )
Main Menu

  * Products
    ( ) ( )
      + Hardware
      + Software
      + 
      + Gaming and Creating
          o GeForce Graphics Cards
          o Laptops
          o G-SYNC Monitors
          o Studio
          o SHIELD TV
      + Laptops and Workstations
          o Laptops
          o NVIDIA RTX in Desktop Workstations
          o NVIDIA RTX in Professional Laptops
          o NVIDIA RTX-Powered AI Workstations
      + Cloud and Data Center
          o Overview
          o Grace CPU
          o DGX Platform
          o EGX Platform
          o IGX Platform
          o HGX Platform
          o NVIDIA MGX
          o NVIDIA OVX
          o DRIVE Sim
      + Networking
          o Overview
          o DPU
          o Ethernet
          o InfiniBand
      + GPUs
          o GeForce
          o NVIDIA RTX / Quadro
          o Data Center
      + Embedded Systems
          o Jetson
          o DRIVE AGX
          o Clara AGX
      + Application Frameworks
          o AI Inference - Triton
          o Automotive - DRIVE
          o Cloud-AI Video Streaming - Maxine
          o Computational Lithography - cuLitho
          o Cybersecurity - Morpheus
          o Data Analytics - RAPIDS
          o Healthcare - Clara
          o High-Performance Computing
          o Intelligent Video Analytics - Metropolis
          o Large Language Models - NeMo Framework
          o Metaverse Applications - Omniverse
          o Recommender Systems - Merlin
          o Robotics - Isaac
          o Speech AI - Riva
          o Telecommunications - Aerial
      + Apps and Tools
          o Application Catalog
          o NGC Catalog
          o NVIDIA NGC
          o 3D Workflows - Omniverse
          o Data Center
          o GPU Monitoring
          o NVIDIA RTX Experience
          o NVIDIA RTX Desktop Manager
          o RTX Accelerated Creative Apps
          o Video Conferencing
          o AI Workbench
      + Gaming and Creating
          o GeForce NOW Cloud Gaming
          o GeForce Experience
          o NVIDIA Broadcast App
          o Animation - Machinima
          o Modding - RTX Remix
          o Studio
      + Infrastructure
          o AI Enterprise Suite
          o Cloud Native Support
          o Cluster Management
          o Edge Deployment Management
          o IO Acceleration
          o Networking
          o Virtual GPU
      + Cloud Services
          o Cloud Gaming
          o Omniverse
          o NeMo
          o BioNeMo
          o Picasso
          o Private Registry
          o Base Command
          o Fleet Command
  * Solutions
      + AI and Data Science
          o Overview
          o AI Inference
          o AI Workflows
          o Conversational AI
          o Data Analytics and Processing
          o Generative AI
          o Machine Learning
          o Prediction and Forecasting
          o Speech AI
      + Data Center and Cloud Computing
          o Overview
          o Accelerated Computing for Enterprise IT
          o Cloud Computing
          o Colocation
          o Edge Computing
          o MLOps
          o Networking
          o Virtualization
      + Design and Simulation
          o Overview
          o 3D Avatars
          o Augmented and Virtual Reality
          o Digital Twins
          o Engineering Simulation
          o OpenUSD Workflows
          o Rendering
      + Robotics and Edge Computing
          o Overview
          o AI-on-5G
          o Edge Deployment Management
          o Edge Solutions
          o Industrial
          o Intelligent Video Analytics
          o Robotics
      + High-Performance Computing
          o Overview
          o HPC and AI
          o Scientific Visualization
          o Simulation and Modeling
      + Self-Driving Vehicles
          o Overview
          o AI Training
          o Chauffeur
          o Concierge
          o HD Mapping
          o Safety
          o Simulation
  * Industries
      + Industries
          o Overview
          o Architecture, Engineering, Construction & Operations
          o Automotive
          o Consumer Internet
          o Cybersecurity
          o Energy
          o Financial Services
          o Healthcare and Life Sciences
          o Higher Education
          o Game Development
          o Manufacturing
          o Media and Entertainment
          o Public Sector
          o Restaurants
          o Retail and CPG
          o Robotics
          o Smart Cities
          o Supercomputing
          o Telecommunications
          o Transportation
  * For You
    ( ) ( ) ( ) ( ) ( ) ( ) ( ) ( ) ( )
      + Creatives/Designers
      + Data Scientists
      + Developers
      + Executives
      + Gamers
      + IT Professionals
      + Researchers
      + Roboticists
      + Startups
      + 
      + NVIDIA Studio
          o Overview
          o Accelerated Apps
          o Products
          o Compare
          o Shop
      + Industries
          o Media and Entertainment
          o Manufacturing
          o Architecture, Engineering, and Construction
          o All Industries >
      + Solutions
          o Data Center/Cloud
          o Laptops/Desktops
          o Augmented and Virtual Reality
          o Multi-Display
          o Rendering
          o Metaverse - Omniverse
          o Graphics Virtualization
          o Engineering Simulation
      + Industries
          o Financial Services
          o Consumer Internet
          o Healthcare
          o Higher Education
          o Retail
          o Public Sector
          o All Industries >
      + Solutions
          o AI Inference
          o AI Workflows
          o Conversational AI
          o Data Analytics
          o Deep Learning Training
          o Generative AI
          o Machine Learning
          o Prediction and Forecasting
          o Speech AI
      + Software
          o AI Enterprise Suite
          o AI Inference - Triton
          o AI Workflows
          o Avatar - Tokkio
          o Cybersecurity - Morpheus
          o Data Analytics - RAPIDS
          o Apache Spark
          o AI Workbench
          o Large Language Models - NeMo Framework
          o Logistics and Route Optimization - cuOpt
          o Recommender Systems - Merlin
          o Speech AI - Riva
          o NGC Overview
          o NGC Software Catalog
          o Open Source Software
      + Products
          o PC
          o Laptops & Workstations
          o Data Center
          o Cloud
      + Resources
          o Professional Services
          o Technical Training
          o Startups
          o AI Accelerator Program
          o Content Library
          o NVIDIA Research
          o Developer Blog
          o Kaggle Grandmasters
      + Developer Resources
          o Join the Developer Program
          o NGC Catalog
          o NVIDIA NGC
          o Technical Training
          o News
          o Blog
          o Forums
          o Open Source Portal
          o NVIDIA GTC
          o Startups
          o Developer Home >
      + Application Frameworks
          o AI Inference - Triton
          o Automotive - DRIVE
          o Cloud-AI Video Streaming - Maxine
          o Computational Lithography - cuLitho
          o Cybersecurity - Morpheus
          o Data Analytics - RAPIDS
          o Healthcare - Clara
          o High-Performance Computing
          o Intelligent Video Analytics - Metropolis
          o Large Language Models - NeMo Framework
          o Metaverse Applications - Omniverse
          o Recommender Systems - Merlin
          o Robotics - Isaac
          o Speech AI - Riva
          o Telecommunications - Aerial
      + Top SDKs and Libraries
          o Parallel Programming - CUDA Toolkit
          o Edge AI applications - Jetpack
          o BlueField data processing - DOCA
          o Accelerated Libraries - CUDA-X Libraries
          o Deep Learning Inference - TensorRT
          o Deep Learning Training - cuDNN
          o Deep Learning Frameworks
          o Conversational AI - NeMo
          o Intelligent Video Analytics - DeepStream
          o NVIDIA Unreal Engine 4
          o Ray Tracing - RTX
          o Video Decode/Encode
          o Automotive - DriveWorks SDK
      + GeForce
          o Overview
          o GeForce Graphics Cards
          o Gaming Laptops
          o G-SYNC Monitors
          o RTX Games
          o GeForce Experience
          o GeForce Drivers
          o Forums
          o Support
          o Shop
      + GeForce NOW
          o Overview
          o Download
          o Games
          o Pricing
          o FAQs
          o Forums
          o Support
      + SHIELD
          o Overview
          o Compare
          o Shop
          o FAQs
          o Knowledge Base
      + Study, Game, Create. Accelerated.
      + Solutions
          o Data Center (On-Premises)
          o Edge Computing
          o Cloud Computing
          o Networking
          o Virtualization
          o Enterprise IT Solutions
      + Software
          o AI Enterprise Suite
          o Cloud Native Support
          o Cluster Management
          o Edge Deployment Management
          o AI Inference - Triton
          o IO Acceleration
          o Networking
          o Virtual GPU
      + Apps and Tools
          o Data Center
          o GPU Monitoring
          o NVIDIA RTX Experience
          o NVIDIA RTX Desktop Manager
      + Resources
          o Data Center & IT Resources
          o Technical Training and Certification
          o Enterprise Support
          o Drivers
          o Security
          o Product Documentation
          o Forums
      + 
          o NVIDIA Research Home
          o Research Areas
          o AI Playground
          o Video Highlights
          o COVID-19
          o NGC Catalog
          o Technical Training
          o Startups
          o News
          o Developer Blog
          o Open Source Portal
          o Cambridge-1 Supercomputer
          o 3D Deep Learning Research
      + Products
          o AI Training - DGX
          o Edge Computing - EGX
          o Embedded Computing - Jetson
      + Software
          o Robotics - Isaac ROS
          o Simulation - Isaac Sim
          o TAO Toolkit
          o Vision AI - Deepstream SDK
          o Edge Deployment Management
          o Synthetic Data Generation - Replicator
      + Use Cases
          o Healthcare and Life Sciences
          o Manufacturing
          o Public Sector
          o Retail
          o Robotics
          o More >
      + Resources
          o NVIDIA Blog
          o Robotics Research
          o Developer Blog
          o Technical Training
          o Startups
  * 

  * NVIDIA GTC
  * Shop
  * Drivers
  * Support

  *  
  *  
    [                    ] 
  *  
  * Login LogOut

Skip to main content

  * 
  *  
  *  
    [                    ]
  *  
  * 0  
  *  
  * Login LogOut

NVIDIA logo

  * Main Menu
  * Products
  * 
      + Hardware
      + 
          o Gaming and Creating
              # GeForce Graphics Cards
              # Laptops
              # G-SYNC Monitors
              # Studio
              # SHIELD TV
          o Laptops and Workstations
              # Laptops
              # NVIDIA RTX in Desktop Workstations
              # NVIDIA RTX in Professional Laptops
              # NVIDIA RTX-Powered AI Workstations
          o Cloud and Data Center
              # Overview
              # Grace CPU
              # DGX Platform
              # EGX Platform
              # IGX Platform
              # HGX Platform
              # NVIDIA MGX
              # NVIDIA OVX
              # DRIVE Sim
          o Networking
              # Overview
              # DPU
              # Ethernet
              # InfiniBand
          o GPUs
              # GeForce
              # NVIDIA RTX / Quadro
              # Data Center
          o Embedded Systems
              # Jetson
              # DRIVE AGX
              # Clara AGX
      + Software
      + 
          o Application Frameworks
              # AI Inference - Triton
              # Automotive - DRIVE
              # Cloud-AI Video Streaming - Maxine
              # Computational Lithography - cuLitho
              # Cybersecurity - Morpheus
              # Data Analytics - RAPIDS
              # Healthcare - Clara
              # High-Performance Computing
              # Intelligent Video Analytics - Metropolis
              # Large Language Models - NeMo Framework
              # Metaverse Applications - Omniverse
              # Recommender Systems - Merlin
              # Robotics - Isaac
              # Speech AI - Riva
              # Telecommunications - Aerial
          o Apps and Tools
              # Application Catalog
              # NGC Catalog
              # NVIDIA NGC
              # 3D Workflows - Omniverse
              # Data Center
              # GPU Monitoring
              # NVIDIA RTX Experience
              # NVIDIA RTX Desktop Manager
              # RTX Accelerated Creative Apps
              # Video Conferencing
              # AI Workbench
          o Gaming and Creating
              # GeForce NOW Cloud Gaming
              # GeForce Experience
              # NVIDIA Broadcast App
              # Animation - Machinima
              # Modding - RTX Remix
              # Studio
          o Infrastructure
              # AI Enterprise Suite
              # Cloud Native Support
              # Cluster Management
              # Edge Deployment Management
              # IO Acceleration
              # Networking
              # Virtual GPU
          o Cloud Services
              # Cloud Gaming
              # Omniverse
              # NeMo
              # BioNeMo
              # Picasso
              # Private Registry
              # Base Command
              # Fleet Command
  * Solutions
  * 
      + AI and Data Science
          o Overview
          o AI Inference
          o AI Workflows
          o Conversational AI
          o Data Analytics and Processing
          o Generative AI
          o Machine Learning
          o Prediction and Forecasting
          o Speech AI
      + Data Center and Cloud Computing
          o Overview
          o Accelerated Computing for Enterprise IT
          o Cloud Computing
          o Colocation
          o Edge Computing
          o MLOps
          o Networking
          o Virtualization
      + Design and Simulation
          o Overview
          o 3D Avatars
          o Augmented and Virtual Reality
          o Digital Twins
          o Engineering Simulation
          o OpenUSD Workflows
          o Rendering
      + Robotics and Edge Computing
          o Overview
          o AI-on-5G
          o Edge Deployment Management
          o Edge Solutions
          o Industrial
          o Intelligent Video Analytics
          o Robotics
      + High-Performance Computing
          o Overview
          o HPC and AI
          o Scientific Visualization
          o Simulation and Modeling
      + Self-Driving Vehicles
          o Overview
          o AI Training
          o Chauffeur
          o Concierge
          o HD Mapping
          o Safety
          o Simulation
  * Industries
  * 
      + Industries
          o Overview
          o Architecture, Engineering, Construction & Operations
          o Automotive
          o Consumer Internet
          o Cybersecurity
          o Energy
          o Financial Services
          o Healthcare and Life Sciences
          o Higher Education
          o Game Development
          o Manufacturing
          o Media and Entertainment
          o Public Sector
          o Restaurants
          o Retail and CPG
          o Robotics
          o Smart Cities
          o Supercomputing
          o Telecommunications
          o Transportation
  * For You
  * 
      + Creatives/Designers
      + 
          o NVIDIA Studio
              # Overview
              # Accelerated Apps
              # Products
              # Compare
              # Shop
          o Industries
              # Media and Entertainment
              # Manufacturing
              # Architecture, Engineering, and Construction
              # All Industries >
          o Solutions
              # Data Center/Cloud
              # Laptops/Desktops
              # Augmented and Virtual Reality
              # Multi-Display
              # Rendering
              # Metaverse - Omniverse
              # Graphics Virtualization
              # Engineering Simulation
      + Data Scientists
      + 
          o Industries
              # Financial Services
              # Consumer Internet
              # Healthcare
              # Higher Education
              # Retail
              # Public Sector
              # All Industries >
          o Solutions
              # AI Inference
              # AI Workflows
              # Conversational AI
              # Data Analytics
              # Deep Learning Training
              # Generative AI
              # Machine Learning
              # Prediction and Forecasting
              # Speech AI
          o Software
              # AI Enterprise Suite
              # AI Inference - Triton
              # AI Workflows
              # Avatar - Tokkio
              # Cybersecurity - Morpheus
              # Data Analytics - RAPIDS
              # Apache Spark
              # AI Workbench
              # Large Language Models - NeMo Framework
              # Logistics and Route Optimization - cuOpt
              # Recommender Systems - Merlin
              # Speech AI - Riva
              # NGC Overview
              # NGC Software Catalog
              # Open Source Software
          o Products
              # PC
              # Laptops & Workstations
              # Data Center
              # Cloud
          o Resources
              # Professional Services
              # Technical Training
              # Startups
              # AI Accelerator Program
              # Content Library
              # NVIDIA Research
              # Developer Blog
              # Kaggle Grandmasters
      + Developers
      + 
          o Developer Resources
              # Join the Developer Program
              # NGC Catalog
              # NVIDIA NGC
              # Technical Training
              # News
              # Blog
              # Forums
              # Open Source Portal
              # NVIDIA GTC
              # Startups
              # Developer Home >
          o Application Frameworks
              # AI Inference - Triton
              # Automotive - DRIVE
              # Cloud-AI Video Streaming - Maxine
              # Computational Lithography - cuLitho
              # Cybersecurity - Morpheus
              # Data Analytics - RAPIDS
              # Healthcare - Clara
              # High-Performance Computing
              # Intelligent Video Analytics - Metropolis
              # Large Language Models - NeMo Framework
              # Metaverse Applications - Omniverse
              # Recommender Systems - Merlin
              # Robotics - Isaac
              # Speech AI - Riva
              # Telecommunications - Aerial
          o Top SDKs and Libraries
              # Parallel Programming - CUDA Toolkit
              # Edge AI applications - Jetpack
              # BlueField data processing - DOCA
              # Accelerated Libraries - CUDA-X Libraries
              # Deep Learning Inference - TensorRT
              # Deep Learning Training - cuDNN
              # Deep Learning Frameworks
              # Conversational AI - NeMo
              # Intelligent Video Analytics - DeepStream
              # NVIDIA Unreal Engine 4
              # Ray Tracing - RTX
              # Video Decode/Encode
              # Automotive - DriveWorks SDK
      + Executives
      + Gamers
      + 
          o GeForce
              # Overview
              # GeForce Graphics Cards
              # Gaming Laptops
              # G-SYNC Monitors
              # RTX Games
              # GeForce Experience
              # GeForce Drivers
              # Forums
              # Support
              # Shop
          o GeForce NOW
              # Overview
              # Download
              # Games
              # Pricing
              # FAQs
              # Forums
              # Support
          o SHIELD
              # Overview
              # Compare
              # Shop
              # FAQs
              # Knowledge Base
      + IT Professionals
      + 
          o Solutions
              # Data Center (On-Premises)
              # Edge Computing
              # Cloud Computing
              # Networking
              # Virtualization
              # Enterprise IT Solutions
          o Software
              # AI Enterprise Suite
              # Cloud Native Support
              # Cluster Management
              # Edge Deployment Management
              # AI Inference - Triton
              # IO Acceleration
              # Networking
              # Virtual GPU
          o Apps and Tools
              # Data Center
              # GPU Monitoring
              # NVIDIA RTX Experience
              # NVIDIA RTX Desktop Manager
          o Resources
              # Data Center & IT Resources
              # Technical Training and Certification
              # Enterprise Support
              # Drivers
              # Security
              # Product Documentation
              # Forums
      + Researchers
      + 
          o 
              # NVIDIA Research Home
              # Research Areas
              # AI Playground
              # Video Highlights
              # COVID-19
              # NGC Catalog
              # Technical Training
              # Startups
              # News
              # Developer Blog
              # Open Source Portal
              # Cambridge-1 Supercomputer
              # 3D Deep Learning Research
      + Roboticists
      + 
          o Products
              # AI Training - DGX
              # Edge Computing - EGX
              # Embedded Computing - Jetson
          o Software
              # Robotics - Isaac ROS
              # Simulation - Isaac Sim
              # TAO Toolkit
              # Vision AI - Deepstream SDK
              # Edge Deployment Management
              # Synthetic Data Generation - Replicator
          o Use Cases
              # Healthcare and Life Sciences
              # Manufacturing
              # Public Sector
              # Retail
              # Robotics
              # More >
          o Resources
              # NVIDIA Blog
              # Robotics Research
              # Developer Blog
              # Technical Training
              # Startups
      + Startups
  * 
      + NVIDIA GTC
      + Shop
      + Drivers
      + Support

Cloud & Data Center
Solutions

  *  
    Accelerated Computing for Enterprise IT
  *  
    Cloud Computing
  *  
    Colocation
  *  
    Edge Computing
  *  
    High Performance Computing
  *  
    Networking
  *  
    Virtualization
  *  
    MLOps

Products

  *  
    Overview
  *  
    DGX
      +  
        DGX Platform
      +  
        DGX Benefits
      +  
        Get DGX
  *  
    NVIDIA-Certified Systems
      +  
        Overview
      +  
        EGX
      +  
        HGX
  *  
    IGX Platform
  *  
    Grace CPU
      +  
        Overview
      +  
        Grace CPU Superchip
      +  
        Grace Hopper Superchip
  *  
    BlueField DPUs
      +  
        Overview
      +  
        Try Project Monterey
  *  
    Where to Buy
  *  
    Test Drive
  *  
    NVIDIA OVX

Data Center GPUs

  *  
    H100
  *  
    L4
  *  
    L40S
  *  
    L40
  *  
    A100
  *  
    A2
  *  
    A10
  *  
    A16
  *  
    A30
  *  
    A40
  *  
    All GPUs*
  *  
    Test Drive

Software

  *  
    Overview
  *  
    AI Enterprise Suite
      +  
        Overview
      +  
        Trial
  *  
    Base Command
  *  
    Bright Cluster Manager
  *  
    CUDA-X
  *  
    Fleet Command
      +  
        Overview
      +  
        Trial
  *  
    Magnum IO
  *  
    NGC Catalog*
  *  
    Networking*
  *  
    Virtualization

Technologies

  *  
    NVIDIA Hopper Architecture
  *  
    NVIDIA Ada Lovelace Architecture
  *  
    NVIDIA Ampere Architecture
  *  
    Confidential Computing
  *  
    NVLink-C2C
  *  
    NVLink/NVSwitch
  *  
    Tensor Cores
  *  
    Multi-Instance GPU
  *  
    IndeX ParaView Plugin
  *  
    NVIDIA Morpheus AI framework*

Resources

  *  
    Overview
  *  
    Applications
  *  
    NVIDIA NGC
  *  
    Technical Training
  *  
    GTC Digital
  *  
    Qualified Server Catalog
  *  
    Where to Buy

Get Started

  * Solutions
      + Accelerated Computing for Enterprise IT
      + Cloud Computing
      + Colocation
      + Edge Computing
      + High Performance Computing
      + Networking
      + Virtualization
      + MLOps
  * Products
      + DGX
      + NVIDIA-Certified Systems
      + IGX Platform
      + Grace CPU
      + BlueField DPUs
      + Where to Buy
      + Test Drive
      + NVIDIA OVX
  * Data Center GPUs
      + H100
      + L4
      + L40S
      + L40
      + A100
      + A2
      + A10
      + A16
      + A30
      + A40
      + All GPUs*
      + Test Drive
  * Software
      + AI Enterprise Suite
      + Base Command
      + Bright Cluster Manager
      + CUDA-X
      + Fleet Command
      + Magnum IO
      + NGC Catalog*
      + Networking*
      + Virtualization
  * Technologies
      + NVIDIA Hopper Architecture
      + NVIDIA Ada Lovelace Architecture
      + NVIDIA Ampere Architecture
      + Confidential Computing
      + NVLink-C2C
      + NVLink/NVSwitch
      + Tensor Cores
      + Multi-Instance GPU
      + IndeX ParaView Plugin
      + NVIDIA Morpheus AI framework*
  * Resources
      + Applications
      + NVIDIA NGC
      + Technical Training
      + GTC Digital
      + Qualified Server Catalog
      + Where to Buy
  * Get Started

 

  * Solutions
      + Solutions
      + Accelerated Computing for Enterprise IT
      + Cloud Computing
      + Colocation
      + Edge Computing
      + High Performance Computing
      + Networking
      + Virtualization
      + MLOps
  * Products
      + Products
      + Overview
      + DGX
          o DGX
          o DGX Platform
          o DGX Benefits
          o Get DGX
      + NVIDIA-Certified Systems
          o NVIDIA-Certified Systems
          o Overview
          o EGX
          o HGX
      + IGX Platform
      + Grace CPU
          o Grace CPU
          o Overview
          o Grace CPU Superchip
          o Grace Hopper Superchip
      + BlueField DPUs
          o BlueField DPUs
          o Overview
          o Try Project Monterey
      + Where to Buy
      + Test Drive
      + NVIDIA OVX
  * Data Center GPUs
      + Data Center GPUs
      + H100
      + L4
      + L40S
      + L40
      + A100
      + A2
      + A10
      + A16
      + A30
      + A40
      + All GPUs*
      + Test Drive
  * Software
      + Software
      + Overview
      + AI Enterprise Suite
          o AI Enterprise Suite
          o Overview
          o Trial
      + Base Command
      + Bright Cluster Manager
      + CUDA-X
      + Fleet Command
          o Fleet Command
          o Overview
          o Trial
      + Magnum IO
      + NGC Catalog*
      + Networking*
      + Virtualization
  * Technologies
      + Technologies
      + NVIDIA Hopper Architecture
      + NVIDIA Ada Lovelace Architecture
      + NVIDIA Ampere Architecture
      + Confidential Computing
      + NVLink-C2C
      + NVLink/NVSwitch
      + Tensor Cores
      + Multi-Instance GPU
      + IndeX ParaView Plugin
      + NVIDIA Morpheus AI framework*
  * Resources
      + Resources
      + Overview
      + Applications
      + NVIDIA NGC
      + Technical Training
      + GTC Digital
      + Qualified Server Catalog
      + Where to Buy
  * Get Started

This site requires Javascript in order to view all its content.
Please enable Javascript in order to access all the functionality of
this web site. Here are the instructions how to enable JavaScript in
your web browser.
[h200-kv-bb]

NVIDIA H200 Tensor Core GPU

The world's most powerful GPU for supercharging AI and HPC workloads.

Notify me when this product becomes available.

Notify Me

Datasheet | Specs

  * Introduction
  * Highlights
  * Benefits
  * Performance
  * NV AI Enterprise
  * Specifications
  * Get Started

  * Introduction
  * Highlights
  * Benefits
  * Performance
  * NV AI Enterprise
  * Specifications
  * Get Started

  * Introduction
  * Highlights
  * Benefits
  * Performance
  * NV AI Enterprise
  * Specifications
  * Get Started

The World's Most Powerful GPU

The NVIDIA H200 Tensor Core GPU supercharges generative AI and
high-performance computing (HPC) workloads with game-changing
performance and memory capabilities. As the first GPU with HBM3e, the
H200's larger and faster memory fuels the acceleration of generative
AI and large language models (LLMs) while advancing scientific
computing for HPC workloads.

NVIDIA Supercharges Hopper, the World's Leading AI Computing Platform

Based on the NVIDIA Hopper(tm) architecture, the NVIDIA HGX H200
features the NVIDIA H200 Tensor Core GPU with advanced memory to
handle massive amounts of data for generative AI and high-performance
computing workloads.

Read Press Release

Highlights

Experience Next-Level Performance

Llama2 70B Inference

1.9X Faster

GPT-3 175B Inference

1.6X Faster

High-Performance Computing

110X Faster

Benefits

Higher Performance and Larger, Faster Memory

Based on the NVIDIA Hopper architecture, the NVIDIA H200 is the first
GPU to offer 141 gigabytes (GB) of HBM3e memory at 4.8 terabytes per
second (TB/s) --that's nearly double the capacity of the NVIDIA H100
Tensor Core GPU with 1.4X more memory bandwidth. The H200's larger
and faster memory accelerates generative AI and LLMs, while advancing
scientific computing for HPC workloads with better energy efficiency
and lower total cost of ownership.

Up to 1.6 Higher Inference Performance with NVIDIA H200

Preliminary measured performance, subject to change.
Llama2 13B: ISL 128, OSL 2K | Throughput | H100 1x GPU BS 64 | H200
1x GPU BS 128
GPT-3 175B: ISL 80, OSL 200 | x8 H100 GPUs BS 64 | x8 H200 GPUs BS
128
Llama2 70B: ISL 2K, OSL 128 | Throughput | H100 1x GPU BS 8 | H200 1x
GPU BS 32.

Unlock Insights with High-Performance LLM Inference

In the ever-evolving landscape of AI, businesses rely on LLMs to
address a diverse range of inference needs. An AI inference
accelerator must deliver the highest throughput at the lowest TCO
when deployed at scale for a massive user base.

The H200 boosts inference speed by up to 2X compared to H100 GPUs
when handling LLMs like Llama2.

Explore NVIDIA's AI Inference Platform

Supercharge High-Performance Computing

Memory bandwidth is crucial for HPC applications as it enables faster
data transfer, reducing complex processing bottlenecks. For
memory-intensive HPC applications like simulations, scientific
research, and artificial intelligence, the H200's higher memory
bandwidth ensures that data can be accessed and manipulated
efficiently, leading up to 110X faster time to results compared to
CPUs.

Learn More About High-Performance Computing
Supercharge High-Performance Computing with NVIDIA H200

Projected performance, subject to change.
HPC MILC- dataset NERSC Apex Medium | HGX H200 4-GPU | dual Sapphire
Rapids 8480
HPC Apps- CP2K: dataset H2O-32-RI-dRPA-96points | GROMACS: dataset
STMV | ICON: dataset r2b5 | MILC: dataset NERSC Apex Medium | Chroma:
dataset HMC Medium | Quantum Espresso: dataset AUSURF112 | 1x H100 |
1x H200.

Better Energy Efficiency and Cost with NVIDIA H200

Preliminary measured performance, subject to change.
Llama2 70B: ISL 2K, OSL 128 | Throughput | H100 1x GPU BS 8 | H200 1x
GPU BS 32

Reduce Energy and TCO

With the introduction of the H200, energy efficiency and TCO reach
new levels. This cutting-edge technology offers unparalleled
performance, all within the same power profile as the H100. AI
factories and supercomputing systems that are not only faster but
also more eco-friendly, deliver an economic edge that propels the AI
and scientific community forward.

Learn More About Sustainable Computing

Performance

Perpetual Innovation Brings Perpetual Performance Gains

GPT-3 175B Inference Performance

Single-node HGX measured performance | A100 April 2021 | H100
TensorRT-LLM Oct 2023 | H200 TensorRT-LLM Oct 2023

The NVIDIA Hopper architecture delivers an unprecedented performance
leap over its predecessor and continues to raise the bar through
ongoing software enhancements with the H100, including the recent
release of powerful open-source libraries like NVIDIA TensorRT-LLM(tm).

The introduction of the H200 continues the momentum with more
performance. Investment in it ensures performance leadership now,
and--with continued improvements to supported software--the future.

[enterprise]

Enterprise-Ready: AI Software Streamlines Development and Deployment

NVIDIA AI Enterprise, together with NVIDIA H200, simplifies the
building of an AI-ready platform, accelerating AI development and
deployment of production-ready generative AI, computer vision, speech
AI, and more. Together, they deliver enterprise-grade security,
manageability, stability, and support to gather actionable insights
faster and achieve tangible business value sooner.

Learn More About NVIDIA AI Enterprise

Specifications

NVIDIA H200 Tensor Core GPU

    Form Factor                         H200 SXM1
FP64                 34 TFLOPS
FP64 Tensor Core     67 TFLOPS
FP32                 67 TFLOPS
TF32 Tensor Core     989 TFLOPS2
BFLOAT16 Tensor Core 1,979 TFLOPS2
FP16 Tensor Core     1,979 TFLOPS2
FP8 Tensor Core      3,958 TFLOPS2
INT8 Tensor Core     3,958 TFLOPS2
GPU Memory           141GB
GPU Memory Bandwidth 4.8TB/s
Decoders             7 NVDEC
                     7 JPEG
Max Thermal Design   Up to 700W (configurable)
Power (TDP)
Multi-Instance GPUs  Up to 7 MIGs @16.5GB each
Form Factor          SXM
Interconnect         NVIDIA NVLink(r): 900GB/s
                     PCIe Gen5: 128GB/s
Server Options       NVIDIA HGX(tm) H200 partner and NVIDIA-Certified
                     Systems(tm) with 4 or 8 GPUs
NVIDIA AI Enterprise Add-on
^1 Preliminary specifications. May be subject to change.
^2 With sparsity.

View Datasheet

Get Started

Notify me when this product becomes available.

Notify Me

NVIDIA H200 Tensor Core GPU Quick Specs

GPU Memory          141GB
GPU Memory          4.8TB/s
Bandwidth
FP8 Tensor Core     4 PetaFLOPS
Performance
Form Factor         SXM
Server Options      NVIDIA HGX(tm) H200 partner and NVIDIA-Certified
                    Systems(tm) with 4 or 8 GPUs
View NVIDIA H200 Datasheet
Products

  * Data Center GPUs
  * NVIDIA DGX Platform
  * NVIDIA EGX Platform
  * NVIDIA HGX Platform
  * Networking Products
  * Virtual GPUs

Technologies

  * NVIDIA Hopper Architecture
  * NVIDIA Ampere Architecture
  * Confidential Computing
  * NVLink-C2C
  * NVLink/NVSwitch
  * Tensor Cores
  * Multi-Instance GPU
  * IndeX ParaView Plugin
  * NVIDIA Morpheus AI framework

Software

  * Overview
  * NVIDIA AI Enterprise
  * Base Command
  * Bright Cluster Manager
  * CUDA-X
  * Fleet Command
  * Magnum IO
  * Networking
  * NGC Catalog
  * NVIDIA NGC
  * Virtualization

Resources

  * Data Center Blogs
  * GPU Apps Catalog
  * Data Center GPUs Product Literature
  * DGX Product Literature
  * Virtual GPU Product Literature
  * GPU Test Drive
  * Where to Buy
  * Qualified System Catalog
  * NVIDIA GRID Community Advisors
  * Virtual GPU Forum

Follow Data Center
    
United Kingdom

  * Privacy Policy
  * Manage My Privacy
  * Legal
  * Accessibility
  * Corporate Policies
  * Product Security
  * Contact

Copyright (c) 2023 NVIDIA Corporation