Ollama — Local AI

Installation & Setup

# macOS
brew install ollama

# Start the server (runs on http://localhost:11434)
ollama serve

# Pull a model
ollama pull llama3.2          # 3B — fast, general purpose
ollama pull llama3.2:1b       # 1B — ultra-fast, low RAM
ollama pull mistral           # 7B — strong reasoning
ollama pull codellama         # code-specialized
ollama pull nomic-embed-text  # embeddings
ollama pull phi4-mini         # Microsoft, small and capable