NVIDIA H200 Tensor Core GPU

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

Now available.

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™ 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.

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.

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.

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.

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.

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.

Performance

Perpetual Innovation Brings Perpetual Performance Gains

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™.

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-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.

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 Power (TDP) Up to 700W (configurable)
Multi-Instance GPUs Up to 7 MIGs @16.5GB each
Form Factor SXM
Interconnect NVIDIA NVLink®: 900GB/s
PCIe Gen5: 128GB/s
Server Options NVIDIA HGX™ H200 partner and NVIDIA-Certified Systems™ with 4 or 8 GPUs
NVIDIA AI Enterprise Add-on

Learn More About Our Data Center Training and Inference Performance.

NVIDIA H200 Tensor Core GPU Quick Specs