Downloading and Installing DeepSeek on Your Computer: How to Use It Locally on Windows, macOS, and Linux

You can install DeepSeek on any computer to use it locally. You don’t even need an Internet connection.

Installing DeepSeek
No comments Twitter Flipboard E-mail
yubal-fernandez

Yúbal Fernández

Writer

Tech journalist with over eight years of experience. I specialize in mobile devices, PCs and consumer tech, as well as software and apps. Head of Xataka Basics, where everyone can find complex tech topics explained in an easy and accessible manner. LinkedIn

We break down how to install DeepSeek on your computer so you can use it whenever you want. There are several ways to do this, but this is one of the easiest. It works on Windows, macOS, and Linux.

To do this, you need a program called Ollama. This program lets you install and use various AI models on your computer, including DeepSeek. Installing Ollama is like installing a regular app, though using it is a bit different.

Its key feature is that it works from the internal console of your operating system, including Windows, macOS, and Linux. This may seem confusing, but it simplifies use. In fact, all you need to do is install the app and type a command to run it.

A key advantage is that you can use DeepSeek without an Internet connection since it runs locally on your computer. The downside is that you won’t be able to search the Internet, at least not with the R1 model.

Installing DeepSeek on Your PC

Installing Ollama

The first step is to go to the Ollama website, which is used to install and run various AI models locally. Visit ollama.com and click the Download button.

Download Ollama

This will take you to a page where you can select your operating system. After choosing it, click Download. By default, the website will detect the system you are using, but you can still download the executable for another system.

Install The Command

Once downloaded, run the installation program. Installing Ollama is simple: Click Next on the splash screen and then Install on the installation screen.

Ollama Run Deepseek

Now comes the only slightly complex part. After installation, open the Ollama app. At first, it might appear that nothing has happened. With Ollama running, open your operating system’s terminal or, for Windows, the Command Prompt. Enter the following commands to install or run DeepSeek, the hot new AI model:

  • ollama pull deepseek-r1:8b: Downloads the 8B version of DeepSeek R1. This version is larger than the smaller versions but more practical.
  • ollama run deepseek-r1:8b: Installs and runs DeepSeek R1 version 8B or the version of your choice.

The installation process requires about 5 GB of storage and depends on your Internet speed. After installation, use the run command to start using it.

How to Use DeepSeek on Your PC

After installation, use the command ollama run deepseek-r1:8b in your computer’s terminal with the Ollama app open. You can replace the 8B version with another available version listed at ollama.com/library/deepseek-r1/tags.

When you start the program, type your question into the command line. After a few seconds, it will generate an answer.

The DeepSeek R1 model specializes in reasoning. When you write a prompt, you’ll see its reasoning process between <think> tags before it generates a response. This allows you to see how the AI model processes your request before providing an answer.

Ollama DeepSeek Think Command

To stop using Ollama with DeepSeek, type the command /bye to return to the default terminal. Typing /? will show other commands you can use.

Images | Xataka On | Markus Spiske (Unsplash) | DeepSeek

Related | GPT o1: What It Is, Differences With Previous Models, and How to Access OpenAI’s New AI Model

Home o Index