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
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.
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.
Once downloaded, run the installation program. Installing Ollama is simple: Click Next on the splash screen and then Install on the installation screen.
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.
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
View 0 comments