# Ollama Configuration
# Docs: https://github.com/ollama/ollama/blob/main/docs/faq.md

# Timezone
TZ=America/Los_Angeles

# Model Storage Location
# OLLAMA_MODELS=/root/.ollama/models

# Max Loaded Models (default: 1)
# OLLAMA_MAX_LOADED_MODELS=1

# Max Queue (default: 512)
# OLLAMA_MAX_QUEUE=512

# Number of parallel requests (default: auto)
# OLLAMA_NUM_PARALLEL=4

# Context size (default: 2048)
# OLLAMA_MAX_CONTEXT=4096

# Keep models in memory (default: 5m)
# OLLAMA_KEEP_ALIVE=5m

# Debug logging
# OLLAMA_DEBUG=1

# GPU Configuration (for GTX 1070)
# OLLAMA_GPU_LAYERS=33  # Number of layers to offload to GPU (adjust based on VRAM)
# OLLAMA_GPU_MEMORY=6GB # Max GPU memory to use (GTX 1070 has 8GB)