# Local LLMs, hands-on: run models on your own machine

> Run LLMs locally with Ollama, llama.cpp and LM Studio. Hardware and memory math, quantization, using local models in code, local RAG and hybrid setups.

Source: https://devaiper.com/courses/local-llms
Published: 2026-10-08

Run, measure and use models on your own hardware, in eight parts. Every part has a short concept video, then a hands-on video where we build it live. The written version of each part appears on this site as its video goes live, with code you can copy.

## Course outline

1. Why run locally, and your first model (coming soon): Privacy, cost and offline use, with a working model.
2. Hardware and memory math (coming soon): Will it fit? Do the arithmetic first.
3. Quantization and choosing a model (coming soon): Size, quality and speed trade-offs.
4. Ollama deep dive (coming soon): Modelfiles, the API and day-to-day use.
5. llama.cpp and LM Studio (coming soon): The engine under the tools.
6. Local LLMs in your code (coming soon): Use a local model from an app.
7. Local RAG (coming soon): Chat with your documents without the cloud.
8. Speed, evals and hybrid with Claude (coming soon): Measure it, then mix local and hosted.

## FAQ

### Can I run an LLM on a laptop without a GPU?

Yes, small quantized models run on CPU. They are slower, so the course shows how to estimate speed and memory before you start.

### Is a local LLM as good as a hosted one?

Usually not at the top end. The course covers when a local model is good enough and how to combine both.