<img alt="" src="https://secure.insightful-enterprise-intelligence.com/783141.png" style="display:none;">

Access NVIDIA H100s from just $2.06/hour. Reserve here

Deploy 8 to 16,384 NVIDIA H100 SXM GPUs on the AI Supercloud. Learn More

NVIDIA H100 SXM

Reserve NVIDIA H100 SXM GPU

Experience the power of NVIDIA HGX SXM5 H100—custom-built on DGX reference architecture. Deploy from 8 to 16,384 cards in a single cluster, exclusively via Hyperstack's Supercloud reservation.

nvidia-hgx-sxm5-h100-reserve-now

Fill In The Form to Reserve NVIDIA H100 SXM - Limited Stock Available

Benefits of NVIDIA H100 SXM

smx-form-factor

SMX Form Factor

High-density GPU configurations, efficient cooling, and energy optimisation with the superior SXM form factor.

largest-single-cluster-of-h100s

Largest Single Cluster of NVIDIA H100 SXMs

With up to 16,384 NVIDIA H100 SXM 80G cards operating in a single cluster, there are no breakpoints, allowing for multitenant capabilities.

built-with-nvidia-dgx-protocols

Built with NVIDIA DGX Protocols

Built on NVIDIA DGX reference architecture, the model provides a comprehensive solution for enterprise-level AI development and applications.

ai-training-&-inference

AI Training & Inference

With 30x faster inference speed and 9x faster training speed compared to the NVIDIA A100, supercharge real-time AI applications, from learning inference to scientific simulations.

llm-performance

LLM Performance

The NVIDIA H100 SXM delivers 30x faster processing than the previous generation for enhancing language model performance.

enhanced-connectivity

Enhanced Connectivity

Operating at 3.2Tb/s using high-throughput, low-latency NVIDIA InfiniBand 'Compute network' for superior data processing and transfer, all nodes can fully utilise their CPU, GPU and Network capabilities without limits.

NVIDIA H100 SXM

Starts from $2.25/hour

nvidia-hgx-sxm5-h100

Technical Specifications

Specification
NVIDIA HGX SXM5 H100
Form factor
8x NVIDIA H100 SXM
FP64
34 teraFLOPS
FP64 Tensor Core
67 teraFLOPS
FP32
67 teraFLOPS
TF32 Tensor Core
989 teraFLOPS
BFLOAT16 Tensor Core
1,979 teraFLOPS
FP16 Tensor Core
1,979 teraFLOPS
FP8 Tensor Core
3,958 teraFLOPS
INT8 Tensor Core
3,958 TOPS
GPU Memory
80GB
GPU Memory Bandwidth
3.35TB/s
Connectivity
3.2 tibps
Decoders
7 NVDEC / 7 JPEG
Multi-instance GPUs
Up to 7 MIGs @10GB each
Max thermal design power (TDP)
Up to 700W (configurable)
Interconnect
NVLink: 900GB/s PCIe / Gen5: 128GB/s

Best in Class

Specifically designed for the deployment of large-scale language models such as Chat GPT, the NVIDIA H100 SXM GPU offers remarkable enhancements. Don’t Miss Out - Reserve now!

nvidia-hgx-sxm5-h100-best-in-class-1

Power the New Era of Generative AI

Build and run real-time inference on trillion-parametre large language models. Enable faster insights, more accurate models, and more efficient operations across a variety of fields.

Transform generative AI and accelerated computing in data processing, electronic design automation, computer-aided engineering and quantum computing. 

2

Frequently Asked Questions

Frequently asked questions about the NVIDIA H100 SXM GPU.

What are the advantages of reserving the NVIDIA H100 SXM GPU?

Reserving the NVIDIA H100 SXM offers several advantages. First, you gain access to some of the most advanced AI clusters of their kind, built on a custom DGX reference architecture. This architecture allows you to deploy anywhere from 8 to an astonishing 16,384 H100 SXM cards in a single cluster – a capability exclusively available through Hyperstack's Supercloud reservation.

Can the NVIDIA H100 SXM be utilised for AI and deep learning applications?

Yes, the NVIDIA H100 SXM GPU can be effectively utilised for AI and deep learning applications, leveraging its exceptional performance and DGX reference architecture.

How can I contact support for questions or assistance regarding the reservation for NVIDIA H100 SXM GPUs?

To contact support for questions or assistance regarding the reservation for NVIDIA H100 SXM GPUs, you can fill out the reservation form to book a meeting and our sales team will reach out to you. Or you can call our sales team directly at +44 (0) 203 475 3402 or email directly at sales@hyperstack.cloud.

Unleash AI with GPU Cloud Power

We build our services around you. Our product support and product development go hand in hand to deliver you the best solutions available.