10 Sentinels Active
SENTINEL 01: [AEGIS] AUDITING POCKETBASE INFRASTRUCTURE...
Back to Self-Hosted Stacks
Ollama

Deploy Ollama

Get up and running with Llama 3, Mistral, Gemma, and other large language models locally.

Quick Start

1

Create a directory

mkdir ollama-self-hosted && cd ollama-self-hosted
2

Create config file

Copy the content from the Config tab below into a file named docker-compose.yml

3

Deploy

docker compose up -d
Fast Track

Deploy Ollama in Minutes

Use our optimized Docker templates to deploy Ollama on any cloud provider. Get $200 in free credit to start on DigitalOcean.

Start with free creditDeploy on DigitalOcean
$200

Metadata

License
MIT
Language
Go
Last Updated
10/14/2026
Category
AI Runners
Deployment ConfigOfficial WebsiteGitHub Repository

Configuration

yaml

# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━
# 🚀 BUILT & MAINTAINED BY THE ALTSTACK
# 🌍 https://thealtstack.com
# 💡 Open-source deployment templates for modern self-hosting.
# ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━

# Docker Compose for Ollama
version: '3.8'

services:
  ollama:
    image: ollama/ollama:latest # Official image
    container_name: ollama
    ports:
      - "11434:11434"
    volumes:
      - ollama_data:/root/.ollama
    networks:
      - ollama_net
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:11434"]
      interval: 30s
      timeout: 10s
      retries: 3
    # Uncomment for NVidia GPU support
    # deploy:
    #   resources:
    #     reservations:
    #       devices:
    #         - driver: nvidia
    #           count: 1
    #           capabilities: [gpu]
    restart: unless-stopped

networks:
  ollama_net:
    driver: bridge

volumes:
  ollama_data:
    name: ollama_data

Community Notes

Help others by adding context, corrections, or warnings about this tool. Sign in to contribute.

No community notes yet. Be the first to add context.