version: "3.8"

services:
  ollama:
    image: ollama/ollama:latest
    container_name: ollama
    restart: unless-stopped
    ports:
      - "${OLLAMA_PORT:-11434}:11434"
    volumes:
      - ollama_data:/root/.ollama
    environment:
      - OLLAMA_HOST=0.0.0.0
      - OLLAMA_NUM_PARALLEL=${OLLAMA_NUM_PARALLEL:-4}
      - OLLAMA_MAX_LOADED_MODELS=${OLLAMA_MAX_LOADED_MODELS:-2}
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

volumes:
  ollama_data: