Ollama: local models the easy way
Ollama packs model weights, runtime and an OpenAI-compatible API into one command. Start with the full lesson, then branch out:
| Ollama basics: install, pull, serve and API |
The one-command version:
ollama pull qwen2.5:7b && ollama run qwen2.5:7b
Everything stays on your machine: no API bills, no data leaving, and it works offline. Pair it with RAG over local documents for a private research assistant.
| Qwen: download, install, fine-tune and use | |
| RAG: answers from your own documents | |
| Prompt engineering that works |