# Run Llama locally on your computer

<a id="short-answer"></a>

To run Llama locally, install a compatible app, download a supported Llama model and load it on your computer. Ollama provides a small Llama 3.2 3B starting point; an existing GGUF needs a separate import step.

Sources checked: 2026-10-26

<a id="first-chat"></a>

## Start with a small local chat

Install Ollama using the [Mac](/learn/mac), [Windows](/learn/windows) or [Linux](/learn/linux) guide. In a terminal, run:

```sh
ollama run llama3.2:3b
```

The first run downloads the model from Ollama. Type a short question, then use `/bye` to leave chat. This command does not download a file from Hugging Bay. The linked Ollama model page documents the command; we have not measured its speed on your computer.

<a id="own-gguf"></a>

## Use a GGUF you downloaded

Find the exact publisher, model version and file in [Llama GGUF search](/browse?q=Llama%20GGUF). Check the file size, app support and upstream terms. A catalogue result can be source information only; check the file row for an actual download.

For a compatible local GGUF, save this line in a file named `Modelfile`, replacing the path with your file:

```text
FROM /absolute/path/to/model.gguf
```

Then create a local Ollama name and open chat:

```sh
ollama create my-local-llama -f Modelfile
ollama run my-local-llama
```

Use the template and any extra files required by the model card and your runner. A GGUF extension alone does not establish support.

<a id="memory-and-checks"></a>

## If it does not load

Start with [Can I run this model?](/learn/can-i-run-a-model). Close other memory-heavy apps and use a modest context length. More context needs more memory. For a split GGUF, obtain all parts of the same release; one shard is not a complete model. Check a short answer against a known fact before using the model for your work.

<a id="learn-sources"></a>

## Sources

- [Ollama Llama 3.2 3B model and command](https://ollama.com/library/llama3.2:3b)
- [Import a model into Ollama](https://docs.ollama.com/import)
- [Ollama context and memory](https://docs.ollama.com/context-length)
- [Meta Llama 3.2 3B Instruct model card](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct)

[Choose a GGUF file](/learn/gguf-download)