[Unit]
Description=Ollama AI inference server (HomeAI)
Documentation=https://ollama.com
After=network-online.target
Wants=network-online.target

[Service]
Type=simple
User=%i
ExecStart=/usr/local/bin/ollama serve
Restart=always
RestartSec=5

# Environment
Environment=OLLAMA_HOST=0.0.0.0:11434
Environment=OLLAMA_MODELS=/usr/share/ollama/.ollama/models

# Limits
LimitNOFILE=65536

# CUDA GPU support
# Uncomment and set if you have multiple GPUs:
# Environment=CUDA_VISIBLE_DEVICES=0

[Install]
WantedBy=default.target