Ollama

Expert guidance for running local LLMs with Ollama.

Triggers

Use this skill when:

• Running LLMs locally for privacy or cost savings
• Setting up offline AI inference
• Managing local model deployments
• Working with open-source models (Llama, Mistral, etc.)
• Developing AI applications without cloud API costs
• Keywords: ollama, local llm, offline, self-hosted, llama, mistral, local model

Installation

# macOS
brew install ollama