Ollama lets you run large language models locally with a single command.

Quick start

ollama run llama3

Why local?

• No API keys or rate limits.
• Data stays on your machine.
• Works offline.

Models I use

• llama3 — general purpose
• codellama — code generation
• nomic-embed-text — embeddings for vector search

A list of the hardware, software, and services I rely on daily.

Editor

VS Code with GitHub Copilot.

Terminal

Bash on Linux.

Languages

Python (via uv), Go, shell scripts.