Maximize the performance of your AI workloads with H100 GPU instances, supporting up to 8 GPUs per instance.
Have you ever reached the limit of your GPU when playing with the latest AI model? H100 SXM instances use NVLink interconnect technology, enabling faster GPU-to-GPU communication. Benchmarks show up to 30% higher compute performance compared to traditional setups.
Accelerate your model serving workloads thanks to Transformer Engine 30x faster for AI inference and new data formats.
Choose 1, 2, or 8 H100 GPUs per instance to match your compute requirements. Need more granularity? The second generation of Secure Multi-Instance GPU (MIG) lets you partition a GPU into isolated instances of the right size — maximizing utilization across workloads of all sizes.
| Characteristics | H100 PCIe | H100 SXM NEW |
|---|---|---|
| GPU | NVIDIA H100 PCIe Tensor Core | NVIDIA H100 Tensor Core |
| GPU memory | up to 2 x 80GB HBM2e | up to 8 x 80GB HBM3 |
| Processor | up to 48 vCPUs AMD Epyc Zen 4 | up to 128 vCPUs Xeon Platinum 8452Y |
| Processor Frequency | 2.7 Ghz | 2 Ghz |
| Memory | up to 480 GB of RAM | up to 960 GB of RAM |
| Memory type | DDR5 | DDR5 |
| Bandwidth | up to 20 Gbps | up to 20 Gbps |
| Storage | Block Storage for the boot and up to 6TB of Scratch Storage NVMe | Block Storage for the boot and up to 12.8TB of Scratch Storage NVMe |
Secure your H100 GPU Instance resource for months or years
| Option | Value | Price |
|---|---|---|
| Zone | Paris 2 | |
| Instance | 1x | 0€ |
| Volume | 10GB | 0€ |
| Flexible IPv4 | Yes | 0.004€ |
| Total | |
|---|---|
| Hourly | 0€ |
| Daily | 0€ |
| Weekly | 0€ |
| Monthly | 0€ |
DC5 is one of Europe's greenest data centers, powered entirely by renewable wind and hydro energy (GO-certified) and cooled with ultra-efficient free and adiabatic cooling. With a PUE of 1.16 (vs. the 1.55 industry average), it slashes energy use by 30-50% compared to traditional data centers.
WAW2 runs on 100% wind power (GO-certified) and uses a combination of direct free cooling, free chilling, immersion systems, and air conditioning to optimize system cooling. With a PUE of 1.32—better than the industry average—it minimizes energy consumption for maximum efficiency.
"Execution difference is 40% in favor of using the H100 PCIe GPUs"
Sovereign AI specialists Golem.ai took a deep technical dive into the topic and shared their findings on our blog. “After running a hundred tests in total between Replicate.com and the H100 de Nvidia hosted by Scaleway, we conclude that the execution difference is 40% in favor of using the H100s,” says Golem.ai’s Kevin Baude.
Understands, interprets, and generates human language in a way that is both meaningful and contextually relevant.
Thanks to models and algorithms specialized in:
Converts spoken language into written text, facilitating the translation of verbal communication into machine-readable data.
Thanks to models and algorithms specialized in:
Generates new content, such as images, text, audio, code. It autonomously produces novel and coherent outputs, expanding the realm of AI-generated content beyond replication or prediction.
With models and algorithms specialized in:
Enables machines to interpret and understand visual information from the world, much like human vision.
Thanks to models and algorithms specialized in:
Predicts and suggests items of interest to users based on their preferences and behaviors, enhancing personalized recommendations and decision-making in various applications.
Using for example Deep Learning Recommendation Model v2 (DLRMv2) that employs DCNv2 cross-layer and a multi-hot dataset synthesized from the Criteo dataset.
| Instance Name | Number of GPU | TFLOPs FP16 Tensor Cores | VRAM | Prices |
|---|---|---|---|---|
| H100-1-80GB | 1 H100 PCIe Tensor Core | Up to 1,513 teraFLOPS | 80GB | €2.73/hour |
| H100-2-80G | 2 H100 PCIe Tensor Core | Up to 3,026 teraFLOPS | 2 x 80GB | €5.46/hour |
| H100-SXM-2-80G/coming soon | 2 H100 Tensor Core | Up to 3,958 teraFLOPS | 2 x 80GB | €6.018/hour |
| H100-SXM-4-80G/coming soon | 4 H100 Tensor Core | Up to 7,916 teraFLOPS | 4 x 80GB | €11.61/hour |
| H100-SXM-4-80G/NEW | 8 H100 Tensor Core | Up to 15,832 teraFLOPS | 8 x 80GB | €23.028/hour |
Benefit from a ready-to-use Ubuntu image to launch your favorite deep learning containers (pre-installed NVIDIA driver and Docker environment).
Easily launch your favorite JupyterLab or Notebook thanks to the pre-installed Docker environment
Access multiple container registries: your own build containers, Scaleway AI containers, NVIDIA NGC registry and any other registry
Access hundreds of AI softwares optimized by Nvidia to maximise the efficiency of your GPUs and boost your productivity. Among hundreds of softwares developed by NVIDIA and tested by leaders of their industry, harness the efficiency of
3TB of Scratch Storage are included in the instance price, but any Block Storage provisioned by you, is at your expense.
For redundancy and thus security reasons we strongly recommend that you provision extra Block Storage volume, as Scratch Storage is ephemeral storage that disappears when you switch off the machine. Scratch Storage purpose is to speed up the transfer of your data sets to the gpu.
How to use Scratch storage then? Follow the guide
These are 2 formats of the same instance embedding NVIDIA H100 PCIe Tensor Core.
NVIDIA announced the H100 to enable companies to slash costs for deploying AI, "delivering the same AI performance with 3.5x more energy efficiency and 3x lower total cost of ownership, while using 5x fewer server nodes over the previous generation."
What inside the product can confirm this announcement?
In addition, at Scaleway we decided to localize our H100 PCIe instances in the adiabatic Data Center DC5. With a PUE (Power User Effectiveness) of 1.15 (average is usually 1.6) this datacenter saves between 30% and 50% electricity compared with a conventional data centre.
Stay tuned for our benchmarks on the topic!
NVIDIA Multi-Instance GPU (MIG) is a technology introduced by NVIDIA to enhance the utilization and flexibility of their data center GPUs, specifically designed for virtualization and multi-tenant environments. It allows a single physical GPU to be partitioned into up to seven smaller Instances, each of which operates as an independent MIG partition with its own dedicated resources, such as memory, compute cores, and video outputs.
Read the dedicated documentation to use MIG technology on your GPU instance
There are many criteria to take into account to choose the right GPU instance:
For more guidance read the dedicated documentation on that topic
NVIDIA NVLink is a high-speed interconnect technology developed by NVIDIA that allows for faster data transfer between GPUs and between GPUs and CPUs.
It is designed to significantly increase the bandwidth and reduce the latency of data transfers compared to traditional PCIe (Peripheral Component Interconnect Express) connections.
This is particularly beneficial in high-performance computing (HPC) and data center environments where multiple GPUs are used in parallel to accelerate computations.
NVLink enables better scalability and efficiency in deep learning, scientific simulations, and other data-intensive applications by providing a more efficient way to share data and workload between GPUs
