Sign up and deploy within minutes

On-demand H100 80GB SXM5

Deploy instances from $3.17/h*

Deploy now

*$2.38/h for a 2-year contract.

$3.17/h for Pay As You Go instances

Partners who trust our services:

Experience the best available GPU for Machine Learning

At the forefront of digital intelligence

Our servers exclusively use the NVIDIA H100 SXM5 80GB NVLINK modules.

Via NVLINK, the H100 achieves a chip-to-chip interconnect bandwidth of 900GB/s and leverages a 3200gbit/s InfiniBand™ interconnect.

$2.38/h for 2-year contract

$3.17/h Pay As You Go instance

Why SXM5?

Unmatched performance and speed

Interconnect bandwidth
Significantly higher interconnect bandwidth, up to 3200 gbit/s RDMA interconnects
Memory bandwidth
SXM5 features faster HBM3 memory with 3 TB/s compared to PCIe’s HBM2e 2 TB/s
Power efficiency
Higher power consumption (700W) compared to PCIe (350W), enabling more intensive computational tasks
Optimized for ML
SXM5 is ideal for large-scale HPC workloads and AI model training on massive datasets

The H100 virtual dedicated servers are powered by:

Up to 8 NVidia® H100 80GB GPUs, each containing 16896 CUDA cores and 528 Tensor Cores.

This is the current flagship silicon from NVidia®, unbeaten in raw performance for AI operations.

We deploy the SXM5 NVLINK module, which offers a memory bandwidth of 2.6 Gbps and up to 900GB/s P2P bandwidth.

Fourth generation AMD Genoa, up to 384 threads with a boost clock of 3.7GHz

The name 8H100.80S.360V is composed as follows: 8x H100 SMX5, 360 CPU core threads & virtualized.

Instance name	GPU model	GPU	CPU	RAM	VRAM	P2P	On demand price	6-month price	2-year price
8H100.80S.176V	H100 SXM5 80GB	8	176	1480	640	/	$25.36/h	$24.35/h	$19.02/h
4H100.80S.120V	H100 SXM5 80GB	4	120	480	320	/	$12.68/h	$12.17/h	$9.51/h
4H100.80S.88V	H100 SXM5 80GB	4	88	740	320	/	$12.68/h	$12.17/h	$9.51/h
2H100.80S.60V	H100 SXM5 80GB	2	60	240	160	/	$6.34/h	$6.09/h	$4.75/h
1H100.80S.30V	H100 SXM5 80GB	1	30	120	80	/	$3.17/h	$3.04/h	$2.38/h

*Note: Once you deploy your instance, the price and discount are fixed and not subject to future changes.

DataCrunch Cloud

Where speed meets simplicity in GPU solutions

Fast Dedicated hardware for max speed and security

Productive Start, stop, hibernate instantly via the dashboard or API

Reliable A historical uptime of over 99.9%

Protected DataCrunch is ISO27001 certified

Reserve your perfect setup today

GPU clusters tailored to your needs

16x H100 Cluster

4x 4H100 bare metal systems

2x Intel Xeon Platinum 8462Y+, total 64C/128T
512GB RAM
7.68TB local NVMe
800gbit InfiniBand
100gbit ethernet
Uplink 5gbit/s

Storage

Up to 300 TB

Tier 1

12 GB/s

Up to 2 PB

Tier 2

3 GB/s

Up to 10 PB

Tier 3

1 GB/s

Pre-order Your Datacrunch GPU clusters

Please fill out the form and we will contact you shortly.

Book a Chat
You can also email us at [email protected]
Your message has been successfully sent!

DataCrunch needs the contact information you provide to us to contact you about our products and services. You may unsubscribe at any time. For information on how to unsubscribe, as well as our privacy practices and commitment to protecting your privacy, check out our Privacy Policy
32x H100 Cluster

4x 8H100 bare metal systems

192C/384T AMD Genoa per node
1536GB DDR5 per node
7.68TB local NVMe
1600gbit InfiniBand
100gbit ethernet
Uplink 5gbit/s

Storage

Up to 300 TB

Tier 1

12 GB/s

Up to 2 PB

Tier 2

3 GB/s

Up to 10 PB

Tier 3

1 GB/s

Pre-order Your Datacrunch GPU clusters

Please fill out the form and we will contact you shortly.

Book a Chat
You can also email us at [email protected]
Your message has been successfully sent!

DataCrunch needs the contact information you provide to us to contact you about our products and services. You may unsubscribe at any time. For information on how to unsubscribe, as well as our privacy practices and commitment to protecting your privacy, check out our Privacy Policy
64x H100 Cluster

8x 8H100 bare metal systems

192C/384T AMD Genoa per node
1536GB DDR5 per node
7.68TB local NVMe
3200gbit InfiniBand
100gbit ethernet
Uplink 10gbit/s

Storage

Up to 300 TB

Tier 1

12 GB/s

Up to 2 PB

Tier 2

3 GB/s

Up to 10 PB

Tier 3

1 GB/s

Pre-order Your Datacrunch GPU clusters

Please fill out the form and we will contact you shortly.

Book a Chat
You can also email us at [email protected]
Your message has been successfully sent!

DataCrunch needs the contact information you provide to us to contact you about our products and services. You may unsubscribe at any time. For information on how to unsubscribe, as well as our privacy practices and commitment to protecting your privacy, check out our Privacy Policy
128x H100 Cluster

16x 8H100 bare metal systems

192C/384T AMD Genoa per node
1536GB DDR5 per node
7.68TB local NVMe
3200gbit InfiniBand
100gbit ethernet
Uplink 25gbit/s

Storage

Up to 300 TB

Tier 1

12 GB/s

Up to 2 PB

Tier 2

3 GB/s

Up to 10 PB

Tier 3

1 GB/s

Pre-order Your Datacrunch GPU clusters

Please fill out the form and we will contact you shortly.

Book a Chat
You can also email us at [email protected]
Your message has been successfully sent!

DataCrunch needs the contact information you provide to us to contact you about our products and services. You may unsubscribe at any time. For information on how to unsubscribe, as well as our privacy practices and commitment to protecting your privacy, check out our Privacy Policy

Looking for something different? Contact us

On-demand H100 80GB SXM5

Experience the best available GPU for Machine Learning

Why SXM5?

Interconnect bandwidth

Memory bandwidth

Power efficiency

Optimized for ML

The H100 virtual dedicated servers are powered by:

DataCrunch Cloud

GPU clusters tailored to your needs

16x H100 Cluster

4x 4H100 bare metal systems

Storage

32x H100 Cluster

4x 8H100 bare metal systems

Storage

64x H100 Cluster

8x 8H100 bare metal systems

Storage

128x H100 Cluster

16x 8H100 bare metal systems

Storage