Docker Compose for Ollama

Ollama local LLM server. Run Llama, Mistral, and other models locally.

ollama llm ai inference

compose.yaml

services:
  ollama:
    image: ollama/ollama:latest
    ports:
      - target: 11434
        mode: host
    healthcheck:
      test:
        - CMD
        - curl
        - -f
        - http://localhost:11434/
      interval: 30s
      timeout: 10s
      retries: 3
    deploy:
      resources:
        reservations:
          cpus: "4"
          memory: 4G
    restart: unless-stopped

Services

ollama ollama/ollama:latest

Edit this template Open in Canvas

Deploy

$ npx defang@latest compose up

Learn more about Defang