Accessible power
Access the NVIDIA Hopper architecture without the complexity of a supercomputer cluster. Perfect for fine-tuning models and running high-throughput inference workloads.
H100 PCIe GPU Instances
Reliable performance for every AI workloads.
Efficient scaling
Deploy single or dual-GPU nodes to match your workload size. The H100 PCIe ensures rapid data transfer between the CPU and GPU for data-intensive applications.
Sovereign and secure
Train on your terms: hosted in Europe (Paris and Warsaw), your proprietary models and datasets remain under EU jurisdiction, immune to extraterritorial regulations.
The standard for enterprise AI
H100 PCIe GPU Instances bring the power of the H100 to a versatile, industry-standard form factor. Designed for organizations that need raw compute power for fine-tuning LLMs, running scientific simulations, or serving massive generative AI models, these instances balance performance with deployment flexibility.
Adapt foundation models to your data. With 80GB of memory per card, the H100 PCIe is ideal for fine-tuning 7B parameter models (and up to 70B with heavy quantization) significantly faster than previous generation hardware.
Serve complex models at scale. Leverage the Transformer Engine to automate FP8 precision, delivering up to 30x faster inference performance for generative AI applications compared to the A100.
The H100 PCIe delivers huge leaps in double-precision (FP64) performance, speeding up fluid dynamics, climate modeling, and molecular dynamics simulations.
Specifications
View pricing- gpu
GPU
NVIDIA H100 PCIe5.
- processor_type
Architecture
NVIDIA Hopper 2022.
- gpu_memory
VRAM
80 GB HBM2E per GPU (2TB/s).
- processor
CPU
24-48 vCPUs AMD EPYC™ 9334.
- bandwidth
Processor frequency
2.7 Ghz.
- memory
RAM
240-480 GB.
- memory_type
RAM type
DDR5.
- bandwidth
Network bandwidth
Up to 20 Gbps.
- storage
Storage
Block Storage and Scratch Local NVMe.
- threads_cores
GPU performance
1513 TFLOPS FP16 Tensor Cores.
- service_level
SLA
99.5%.
Customer success stories
Execution time cut by 40% vs other providers
Sovereign AI specialists Golem.ai conducted a rigorous benchmark comparing Replicate.com against Scaleway’s infrastructure. After running over 100 tests, their technical deep dive revealed a 40% execution speed advantage in favor of Scaleway’s dedicated NVIDIA H100 GPUs.
Estimate your GPU costs
Choose your plan
Estimated cost
| Option and value | Price |
|---|---|
| ZoneParis 2 | |
| Instance1x | 0€ |
| Volume10GB | 0€ |
| Flexible IPv4No | 0€ |
100% renewable energy, up to 30% less power
DC5 (PAR2) 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% compared to traditional data centers.
Looking for more power? Discover our full range.
H100-SXM
Accelerate AI applications' development with H100-SXM GPU Instances.
B300-SXM
Push the boundaries of performance with NVIDIA's Blackwell architecture.
Managed Inference
Deploy AI models in a dedicated inference infrastructure, with tailored security and predictable throughput.
Choose the cloud built for what's next
Customer data sovereignty
Dependency is the enemy of resilience. Customers want their data hosted by a regional provider. Gain sovereignty with our multi-cloud tools & infrastructure.
Sustainable data centers
We recycle our hardware, only use renewable energy and pay close attention to our water usage. Also, our Power Usage Effectiveness (PUE) is displayed online 24/7 for you to see for yourself.
Low latency
Every complete cloud ecosystem needs 100% reliability, which is why we provide nine Availability Zones in three different regions.
Frequently asked questions
What's the difference between H100-1-80G and H100-2-80G?
These are 2 formats of the same instance embedding NVIDIA H100 PCIe Tensor Core.
- H100-1-80G embeds 1 GPU NVIDIA H100 PCIe Tensor Core, offering a GPU memory of 80GB
- H100-2-80G embeds 2 GPUs NVIDIA H100 PCIe Tensor Core, offering a GPU memory of 2 times 80GB. This instance enables faster time to train for bigger Transformers models that scale 2 GPUs at a time. T
How can I use MIG to get the most out of my GPU?
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.
How to choose the right GPU for my workload?
There are many criteria to take into account to choose the right GPU instance:
- Workload requirements
- Performance requirements
- GPU type
- GPU memory
- CPU and RAM
- GPU driver and software compatibility
- Scaling
For more guidance read the dedicated documentation on that topic
What is NVlink?
NVLink is a high-speed interconnect technology developed by NVIDIA that allows for faster data transfer between GPUs and between GPUs and CPUs.
It's 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.
Learn more here.
How fast can I start my cloud GPU rental?
You can spin up resources in minutes. Create a Scaleway account, set up your IAM permissions, and follow the console instructions to deploy your H100 PCIe cloud GPU.