---
title: "Running Local LLMs with Ollama"
date: 2026-04-02
draft: false
tags: ['ollama', 'llm', 'tools', 'linux']
---

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

## Quick start

```bash
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