version: "3.8"

services:
  localai:
    image: localai/localai:latest-gpu-nvidia-cuda-12
    container_name: localai
    restart: unless-stopped
    ports:
      - "${LOCALAI_PORT:-8080}:8080"
    volumes:
      - localai_models:/build/models
    environment:
      - THREADS=${THREADS:-4}
      - CONTEXT_SIZE=${CONTEXT_SIZE:-4096}
      - MODELS_PATH=/build/models
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

volumes:
  localai_models: