Ollama

Ollama is a command line tool for running large language models on your local computer. It allows users to download and run models like Llama 2, Code Llama and others locally, and supports customization and creation of their own models. This free and open source project currently supports macOS and Linux operating systems, and will also support Windows systems in the future.

In addition, Ollama also provides an official Docker image, making it easier to deploy large language models using Docker containers, ensuring that all interactions with these models occur locally without the need to send private data to third-party services. Ollama supports GPU acceleration on macOS and Linux and provides a simple command line interface (CLI) as well as a REST API for interacting with applications.

This tool is particularly useful for developers or researchers who need to run and experiment with large language models on their local machine, without relying on external cloud services.

Ollama has now launched the Ollama desktop version for macOS and Windows, with new file processing and multi-modal interaction functions, allowing users to interact with local large language models more intuitively and conveniently.

Obtaining the Ollama installation package

Obtain the Ollama installation package, scan the QR code and follow the reply: Ollama

Ollama supported models

Ollma provides a model library. Users can choose to install the model they want to run. Currently, it supports 40+ models and is still increasing. The following are examples of open source models that can be downloaded: