Ollama is a user-friendly software package designed to run large language models locally on your computer. It is available for MacOS, Linux, and Windows. To get started with Ollama, you download and install the software, then use commands to pull models from the library or a model configuration file. The library includes many free open-source models, which you can explore on the Ollama website.
To run large language models with Ollama, you’ll need a reasonably powerful computer. As a general guideline, you should have at least 8GB of RAM for 7B models, 16GB for 13B models, and 32GB for 33B models.