GPU Cloud

99.99% Uptime SLA

50% Cost Savings

EU Data Sovereignty

Human Support

G6 Instances – A great starting point for AI/ML

Our G6 instances can be launched with 1–4 Nvidia L4 GPUs and are a great choice for teams looking to develop their first AI/ML workloads.

Instance	GPUs	vCPU	Memory (GIB)	Storage (GB)	Baseline bandwidth	Burst bandwidth	Private Network	Price per hour*	Price per month
LSW.G6.XLARGE	1	4	16	250	5 Gbps	15 Gbps	2.5 Gbps	€0,6147	€403,88
LSW.G6.2XLARGE	1	8	32	450	5 Gbps	15 Gbps	2.5 Gbps	€0,6988	€459,10
LSW.G6.4XLARGE	1	16	64	600	5 Gbps	15 Gbps	2.5 Gbps	€0,8241	€541,45
LSW.G6.8XLARGE	1	32	128	900	5 Gbps	15 Gbps	2.5 Gbps	€0,9653	€634,22
LSW.G6.16XLARGE	1	64	256	1800	5 Gbps	15 Gbps	2.5 Gbps	€1,6281	€1069,65
LSW.GR6.4XLARGE	1	16	128	600	5 Gbps	15 Gbps	2.5 Gbps	€0,7369	€485,92
LSW.GR6.8XLARGE	1	32	256	900	5 Gbps	15 Gbps	2.5 Gbps	€1,1766	€773,05
LSW.G6.18XLARGE	2	72	288	1800	5 Gbps	15 Gbps	2.5 Gbps	€1,8243	€1210,64
LSW.G6.12XLARGE	4	48	192	4200	5 Gbps	15 Gbps	2.5 Gbps	€2,4699	€1622,00
LSW.G6.24XLARGE	4	96	384	4200	5 Gbps	15 Gbps	2.5 Gbps	€3,2081	€2107,75
* Hourly pricing: Storage is charged per gigabyte-hour. * 1 TB pooled internet traffic per month, shared across your instances, with free incoming traffic to help you avoid surprise egress costs. * Each GPU is independent, ideal for running multiple models in parallel. * Each GPU supports flexible precision (FP16, INT8, INT4) to optimize speed and cost-efficiency for your workloads.

Get Started

How does bandwidth work for G6 instances?

Each account gets 1 TB of pooled internet traffic per month, shared across all Public Cloud instances. Incoming traffic is always free, helping you avoid unexpected costs. Following is the breakdown of costs in case you exceed the monthly 1TB allowance:

Bandwidth	Quantity	Price per TB	Price per GB
	<1	Free tier	Free tier
Outgoing	>1.00	€2,20	€0,0022
	10	€1.90	€0.0019
	15	€1.50	€0.0015
	30	€1.36	€0.0014
	50	€1.20	€0.0012
	100	€1.00	€0.0010

How to Launch a GPU Instance on Leaseweb Public Cloud

Sign Up

Click on Sign Up to add Public Cloud to your cart.

Checkout

Proceed to checkout and complete the order with the €1 setup fee.

Create Your Account

Fill in your personal or company details to create your Leaseweb account.

Verification

We’ll start the customer verification process and email you once approved.

Log In to the Customer Portal

Once verified, log in using your details at leaseweb.com.

Go to Public Cloud

From the left navigation menu, select Public Cloud → Instances.

Launch a GPU Instance

Click Launch Instance, choose a GPU Optimized flavor, and configure your instance.

Deploy

Click Launch & your GPU instance will be ready within minutes!

Designed for Teams Like Yours

AI & ML engineers

Train and run ML models like ResNet-25M, RNNT-120M, GPT-6B, Mistral-7B

Developers & Startups

Build, test, and deploy AI prototypes or inference workloads

Graphics & 3D Teams

Rendering, game streaming, real-time CGI

Remote Teams / Virtual Workstations

GPU-powered desktops for multiple users

Benefits of Leaseweb

Flexibility

Spin instances up or down instantly to match your workloads.

AWS Compatible APIs

Automate with REST, CLI, or Terraform, fully EC2-compatible.

Regional Availability

Live in NL & DE for EU compliance, US/Canada coming soon.

Service Monitoring

Built-in checks, status updates, and alerts at no extra cost.

Advanced User Interface

Manage networks, storage, SSH, firewalls, and backups with ease.

Transparent & Flexible Billing

Clear upfront pricing with hourly or monthly options.

Usage Visibility & Control

Full usage insights and resource management via portal.

EU Data Sovereignty

Amsterdam-based, 100% GDPR-compliant.

Why Businesses Choose Leaseweb

"We wanted a party with a good continuous hosting infrastructure and high uptime. Dell recommended Leaseweb, and they were the only provider on the market that offered what we were looking for."

"You feel like the customer value at Leaseweb is very high. Small problems can have a big impact on our games, so we need a partner like Leaseweb.”

"I know Leaseweb by reputation and excellent pricing models. This was a major determining factor in our decision to choose Leaseweb as our IaaS provider"

Start Running your AI Workloads on our Enterprise-Grade GPU Cloud

Spin up 1–4 NVIDIA L4 GPUs on-demand with predictable performance, full EU data sovereignty, and up to 50% lower costs than hyperscalers.

Frequently Asked Questions

How can I get Started?

To get started, you must first create an account with Leaseweb which means going through our customer verification process by paying a one-time payment fee of €1.00.

Once you have your account ready, you will have instant access to our Customer Portal, and from there you can start launching instances.

Are CPU and GPU resources dedicated?

GPUs on G6 instances are fully dedicated to your workloads, while vCPUs are shared. This setup gives you cost-efficient compute while ensuring predictable GPU performance.

What kind of Uptime can I expect with G6 instances?

All G6 Public Cloud instances are backed by a 99.99% uptime SLA, ensuring your workloads stay running reliably so you can focus on your work, not infrastructure.

Can I train LLMs on G6 instances?

G6 is best suited for ML model training and LLM inference. Large LLM training is not recommended due to GPU memory limits.

What model sizes can I run?

G6 instances support ML models like ResNet-25M, RNNT-120M, and smaller LLMs such as GPT-6B, Mistral-7B, or other smaller LLMs up to a few billion parameters.

Can I run multiple models in parallel on a multi-GPU instance?

Yes, on multi-GPU G6 instances, each GPU runs independently, so you can deploy multiple models or tasks across GPUs simultaneously without them interfering with each other.

How do I manage instances programmatically?

Fully automatable via REST API, CLI, or Terraform, AWS EC2 compatible.

Can I monitor GPU usage and performance?

Real-time metrics, customizable alerts, and usage dashboards are available in the Customer Portal.

What backup and recovery options are available?

Snapshots, GRML, and Acronis integration for robust data protection.

Can I use G6 instances for graphics workloads or virtual desktops?

Yes, G6 supports GPU-accelerated rendering, game streaming, image processing, and VDI for multiple users.

Can I integrate G6 instances with my existing cloud workflows?

API compatibility with AWS EC2 and Terraform allows easy integration with your current infrastructure.

Enterprise Grade GPU Cloud at SMB Prices