Ollama is a software package that offers an easy way to run large language models locally on your computer. It has versions available for MacOS, Linux, and Windows. To use Ollama, you simply download and install it, then run commands to pull models from the library or from a model configuration file. It supports many free open-source models which can be viewed on the Library section of the Ollama website. You’ll need a reasonably powerful computer to run large language models with Ollama. As a general guideline, you should have at least 8GB RAM for 7B models, 16GB for 13B models, and 32GB for 33B models.