Ollama is a command-line tool for running large language models on a local computer, allowing users to download and run models such as Llama 2, Code Llama, and others locally, and supporting customization and the creation of their own models. This free and open-source project currently supports macOS and Linux operating systems, and will also support Windows in the future.
In addition, Ollama also provides an official Docker image, making it simpler to deploy large language models using Docker containers, ensuring that all interactions with these models take place 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 a local machine, without relying on external cloud services.
Ollama has now launchedOllama Desktopfor macOS and Windows, adding file processing and multimodal interaction features, making interaction with local large language models more intuitive and convenient for users.
How to obtain the Ollama installation package
Obtainthe Ollama installation package, scan the QR code to follow and reply:Ollama
Models supported by Ollama
Ollama provides a model library, and users can choose to install the models they want to run. It currently supports 40+ models, and is still continuously increasing. The following are examples of open-source models that can be downloaded:
| Model | Parameter size | File size | Download and run command |
|---|---|---|---|
| DeepSeek-R1 | 1.5B, 7B, 14B, 32B, etc. | 12-320GB | ollama run deepseek-r1 |
| Neural Chat | 7B | 4.1GB | ollama run neural-chat |
| Starling | 7B | 4.1GB | ollama run starling-lm |
| Mistral | 7B | 4.1GB | ollama run mistral |
| Llama 2 | 7B | 3.8GB | ollama run llama2 |
| Code Llama | 7B | 3.8GB | ollama run codellama |
| Llama 2 Uncensored | 7B | 3.8GB | ollama run llama2-uncensored |
| Llama 2 13B | 13B | 7.3GB | ollama run llama2:13b |
| Llama 2 70B | 70B | 39GB | ollama run llama2:70b |
| Orca Mini | 3B | 1.9GB | ollama run orca-mini |
| Vicuna | 7B | 3.8GB | ollama run vicuna |
