How to Install Ollama on a VPS

How to Install Ollama on a VPS

Ollama makes it easy to run large language models locally on your Breeze. It handles model downloading, quantization, and serving behind a simple CLI and REST API.

Requirements

• A Breeze with at least 8 GB RAM (16 GB+ recommended for larger models)
• Ubuntu 22.04 or newer
• Root or sudo access

Installation

Run the official install script:

curl -fsSL https://ollama.com/install.sh | sh

Verify the installation:

ollama --version

Pull and Run a Model

Download and run a model such as Llama 3:

ollama pull llama3
ollama run llama3

Run as a Service

Ollama installs a systemd service automatically. Manage it with:

sudo systemctl status ollama
sudo systemctl restart ollama

Expose the API

By default Ollama listens on localhost:11434. To bind to all interfaces, set the environment variable:

sudo systemctl edit ollama

Add Environment="OLLAMA_HOST=0.0.0.0" under the [Service] section, then restart. Use a firewall to restrict access to trusted IPs only.