ollama/compose.yaml

services:
  ollama:
    image: ollama/ollama:${OLLAMA_IMAGE_TAG:-latest}
    container_name: ollama
    restart: unless-stopped

    # Keep it local by default, expose it later if you need to.
    ports:
      - "${OLLAMA_BIND_IP:-127.0.0.1}:11434:11434"
    deploy:                     # For GPU
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

                # Persistent models and server state.
    volumes:
      - ollama:/root/.ollama

    environment:
      # The official image already defaults to 0.0.0.0:11434 inside the container,
      # but keeping it explicit helps when you override things later.
      - OLLAMA_HOST=0.0.0.0:11434

      # Service tuning.
      - OLLAMA_KEEP_ALIVE=${OLLAMA_KEEP_ALIVE:-5m}
      - OLLAMA_NUM_PARALLEL=${OLLAMA_NUM_PARALLEL:-1}
      - OLLAMA_MAX_LOADED_MODELS=${OLLAMA_MAX_LOADED_MODELS:-1}
      - OLLAMA_NUM_THREADS=${OLLAMA_NUM_THREADS:-16}

      # Optional, but relevant when a browser-based UI talks to Ollama directly.
      # See the Networking section for why this exists.
      - OLLAMA_ORIGINS=${OLLAMA_ORIGINS:-}

    # GPU reservation is a separate section below.
    # Add it only on hosts that actually have NVIDIA GPUs.
      - NVIDIA_VISIBLE_DEVICES=all
      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
      - OLLAMA_FLASH_ATTENTION=1        # Optional: better performance

volumes:
  ollama: {}