NVIDIA H100

The NVIDIA H100 is an ideal choice for large-scale AI applications. It uses the NVIDIA Hopper architecture that combines advanced features and capabilities, accelerating AI training and inference on larger models. Starting from $1.80/hr

Available at the most cost-effective pricing

Launch your AI products faster with on-demand GPUs and a global network of data center partners

Virtual machines

The ideal deployment strategy for AI workloads with a H100.

from $1.80/hr

Save up to 35% with commitment pricing Launch an instance
  1. Up to 8 GPUs / virtual machine
  2. Flexible
  3. Network attached storage
  4. Private networks
  5. Security groups
  6. Images

Bare metal

Complete control over a physical machine providing absolute performance & control

Powered by renewable energy
  1. Up to 8 GPUs / host
  2. No noisy neighbours
  3. SpectrumX local networking
  4. 300Gbps external connectivity
  5. NVMe SSD storage

Looking to scale? Please contact us for enterprise solutions.

Speak with an expert

The NVIDIA H100 is perfect for a wide range of workloads

Deploying AI based workloads on CUDO Compute is easy and cost-effective. Follow our AI related tutorials.

Specifications

Starting from $1.80/hr
Architecture NVIDIA Hopper
Form factorSXM | NVL
FP64 tensor core67 TFLOPS | 60 TFLOPS
FP3267 TFLOPS | 60 TFLOPS
FP32 tensor core989 TFLOPS | 835 TFLOPS
BFLOAT16 tensor core1,979 TFLOPS | 1,671 TFLOPS
FP16 tensor core1,979 TFLOPS | 1,671 TFLOPS
FP8 tensor core3,958 TFLOPS | 3,341 TFLOPS
INT8 tensor core3,958 TOPS | 3,341 TOPS
GPU memory80GB | 94GB
GPU memory bandwidth3.35 TB/s | 3.9 TB/s
Decoders7x NVDEC 7x NVJPEG
Max thermal design power (TDP)Up to 700W | 350-400W
Multi-instance GPUs (MIG)Up to 7 MIGs @10GB each | Up to 7 MIGs @12GB each
InterconnectNVLink: 900GB/s PCIe Gen5: 128GB/s | NVLink: 600GB/s PCIe Gen5: 128GB/s

Use cases

AI Inference

Engineers and scientists across various domains can leverage the NVIDIA H100 to accelerate AI inference workloads, such as image and speech recognition. The H100's powerful Tensor Cores enable it to quickly process large amounts of data, making it perfect for real-time inference applications.

Deep Learning

The NVIDIA H100 Tensor Core GPU offers a diverse range of use cases for deep learning on larger models. The H100 revolutionizes deep learning for data scientists and researchers, allowing them to handle large datasets and perform complex computations for training deep neural networks.

High-Performance Computing

Many diverse organizations can deploy the NVIDIA H100 GPU to accelerate high-performance computing workloads, such as scientific simulations, weather forecasting, and financial modeling. With its high memory bandwidth and powerful processing capabilities, the H100 makes it easy to run workloads at every scale.

Browse alternative GPU solutions for your workloads

Access a wide range of performant NVIDIA and AMD GPUs to accelerate your AI, ML & HPC workloads

NVIDIA H200

NVIDIA H200

Get the highest performing H200 GPUs at scale on our reserved cloud.

NVIDIA B100

NVIDIA B100

Get the highest performing B100 GPUs at scale on our reserved cloud.

NVIDIA A40

NVIDIA A40

Utilise our on-demand cloud and quickly deploy high performing A40 GPUs.

NVIDIA L40S

NVIDIA L40S

Utilise our on-demand cloud and quickly deploy high performing L40S GPUs.

NVIDIA A100 PCIe

NVIDIA A100 PCIe

Utilise our on-demand cloud and quickly deploy high performing A100 PCIe GPUs.

NVIDIA V100

NVIDIA V100

Utilise our on-demand cloud and quickly deploy high performing V100 GPUs.

NVIDIA RTX A4000

NVIDIA RTX A4000

Utilise our on-demand cloud and quickly deploy high performing RTX A4000 GPUs.

NVIDIA RTX A5000

NVIDIA RTX A5000

Utilise our on-demand cloud and quickly deploy high performing RTX A5000 GPUs.

NVIDIA RTX A6000

NVIDIA RTX A6000

Utilise our on-demand cloud and quickly deploy high performing RTX A6000 GPUs.

AMD MI250/300

AMD MI250/300

Get the highest performing MI250/300 GPUs at scale on our reserved cloud.

An NVIDIA preferred partner for compute

We're proud to be an NVIDIA preferred partner for compute, offering the latest GPUs and high-performance computing solutions.

Also trusted by our other key partners:

  • AMD logo
  • blendergrid logo
  • nucocloud logo
  • dpp logo

Frequently asked questions

Are you looking for support with something more specific? Check our our knowledge base

Pricing & reservation enquiry

Enquire about access today to test the H100 GPU Cloud, or reserve your H100 Cloud on CUDO Compute for as long as you want it, with unique contracts tailored to suit your needs.

Get started today or speak with an expert...