Self-host Ollama: Llama 3 8B with Docker

Meta's Llama 3 8B model, served locally through Ollama's HTTP API.

This page describes the Levelrail template for Ollama: Llama 3 8B (AI). It deploys the services below as one Docker Compose app on your own server.

Project site: https://ollama.com/library/llama3.

Recommended memory: about 7168 MiB.

Services, ports and volumes

Service	Image	Container ports	Volumes
ollama	ollama/ollama:0.33.3	11434	ollama_data -> /root/.ollama

Environment variables

This template sets no environment variables.

Passwords and keys marked as generated are created for you when the app is deployed and stored as secrets. Values are not shown here.

Deploy Ollama: Llama 3 8B with Levelrail

In the dashboard, open Apps, choose New app, then Browse templates, and select Ollama: Llama 3 8B. Review the Compose body and deploy.

With the CLI:

levelrail-cli templates deploy ollama-llama3 --name my-ollama-llama3

See Service template catalog for how templates work, and Getting started if you have not installed Levelrail yet.

More AI templates

• AnythingLLM
• ComfyUI
• Flowise
• Flowise (Postgres + Qdrant)
• Jupyter GPU Notebook
• Label Studio

All templates are listed in the self-host gallery.