VM Templates

You can quickly launch a pre-configured Virtual Machine (VM) from a set of ready-to-use templates. These templates save you time by providing a secure base system or pre-installed environments for machine learning and development.

Explore the available templates here: VM Templates Console

How it works

Pre-configured VMs run as containers with VM-like functionality:

Full SSH access – Connect with your preferred terminal or IDE
Persistent storage – Your data persists across sessions
GPU support – Available on compatible templates
Container efficiency – Faster startup than traditional VMs

Operating System Templates

Ubuntu VM

Lightweight Ubuntu Linux VM with full SSH access. Ideal for configuring your own stack from scratch.

Alpine VM

Minimal Alpine Linux VM with SSH access. Optimized for low resource usage and custom configurations.

Debian VM

Stable Debian Linux VM with SSH access. Suitable for production environments and enterprise applications.

CentOS VM

Enterprise-grade CentOS Linux VM with SSH access. Best for Red Hat-based deployments and workloads requiring CentOS compatibility.

Fedora VM

Modern Fedora Linux VM with SSH access. A good choice for cutting-edge development, testing, and package availability.

Arch Linux VM

Minimalist Arch Linux VM with SSH access. Recommended for advanced users who need fine-grained customization.

Machine Learning Templates

PyTorch Conda CUDA

A PyTorch environment pre-configured with Conda package manager and CUDA support, enabling GPU-accelerated deep learning development.

TensorFlow

An official TensorFlow environment ready for machine learning model development, training, and deployment.

Next Steps

Go to the VM Templates Console
Choose your template
Select GPU and resources (if needed)
Add SSH key for access
Click Deploy

Your environment will be ready in 30-60 seconds.

Key Benefits

Faster setup – no need to manually install base OS or ML frameworks
Full SSH access – complete control over your VM
Choice of environment – start from a minimal OS or a pre-built ML stack
Consistency – reproducible environments across deployments

Use cases

Web development

Ubuntu/Debian VMs for LAMP/MEAN stacks
Full package manager access
Custom software installation

Machine learning

PyTorch/TensorFlow VMs with CUDA pre-configured
Jupyter notebooks ready to use
Large datasets and model storage

Microservices

Alpine VMs for minimal footprint
Container orchestration testing
CI/CD pipeline integration

Best practices

Choose the right template

Start with Ubuntu for general use
Use Alpine for minimal resource needs
Pick ML templates for AI/ML workloads

Security

Always add your SSH key during deployment
Update packages after first login
Configure firewall rules as needed

VM Templates

On this page