# Copy to .env and adjust. All values below are defaults baked into
# docker-compose.yml — only uncomment/change what you actually want to override.

# --- llama.cpp / model ---
LLAMA_MODEL_FILE=Qwen3.8-27B-UD-Q4_K_XL.gguf
LLAMA_GPU_LAYERS=999
# 65536 (64K) fits comfortably in 32GB VRAM alongside the model weights.
# Raise toward 131072 if you need more context; see docs/research/qwen3.8-27b-quant.md
# for the VRAM math at larger context sizes.
LLAMA_CTX_SIZE=65536
LLAMA_PORT=8080

# --- Open WebUI ---
WEBUI_PORT=3000
# Dummy key — llama.cpp's OpenAI-compatible endpoint doesn't check it, but
# Open WebUI requires the field to be non-empty.
OPENAI_API_KEY=local

# --- Lazytainer ---
# Seconds of inactivity before llama-server is stopped. 900 = 15 min.
LAZYTAINER_INACTIVE_TIMEOUT=900