Complete Guide to Install DeepSeek on Windows

DeepSeek it has become one of the artificial intelligence most talked about due to its ability to work locally and without the need for an Internet connection. In this article, we will teach you how to install this IA on your computer with Windows and how to get the most out of it with tools like Don't y LM Studio, options that stand out for their versatility and ease of use. Here you will find all the necessary steps in detail, avoiding complicated technicalities and promoting a installation no hiccups.

The process is also viable for others OS , the MacOS o GNU / Linux, but we will focus on the installation on Windows. The advantages of having DeepSeek running on your local PC are many, from greater control over your data to the ability to use AI offline at any time. Let's look at it step by step.

What do you need to install DeepSeek?

Before you begin, make sure you have the following:

• A Windows computerIt also works on macOS or GNU/Linux if you decide to try it on another machine later.
• At least 5 GB of free space on your hard drive to install the stripped-down version of DeepSeek.
• Internet connection to perform the initial download of the necessary software and AI model.
• Patience, since some downloads may take time depending on your internet speed.

Although you can install a more advanced version of DeepSeek (such as the 671 GB version), these require much more demanding technical specifications. For this guide, we will use version 8B, which is lighter and more functional for regular users.

Step 1: Download and install Ollama

Ollama is an essential tool for running DeepSeek on your computer. This software allows you to run the AI ​​model locally and in an accessible manner. Follow these steps:

1. Access the official page of Don't (ollama.com).
2. Download the version of the program compatible with your operating system. For Windows, this is an executable file (.exe).
3. Double-click the downloaded file to start the installation process.
4. Follow the on-screen instructions. You will only have to press "Install" and wait a few minutes for the installation to finish.

Once Ollama is installed, you will not see a Graphic interface traditional, since it works from the terminal or symbol of the system on Windows. This may sound complicated, but it's actually easier than it seems.

If you want to know how to install Android apps on Windows 11 from Google Play, such as DeepSeek, Gemini, ChatGPT, etc., on your PC, check out this tutorial.

Step 1: Download the DeepSeek RXNUMX model

With Ollama up and running, the next step is to download the AI ​​model you want to use. Here we'll focus on version 8B, which is ideal for computers that don't have very advanced specs.

• Open the command prompt in Windows. You can do this by typing "Cmd" in the search bar.
• Enter the following command to download the model: ollama pull deepseek-r1:8b. This will start the download of the reduced DeepSeek model.
• Please wait patiently, the file is approximately 4.7 GB. Do not close the window or turn off your PC during this process.

Once the download is complete, the model is ready to use. Let's move on to the next step!

Step 3: Running DeepSeek

With the model downloaded, you can now start interacting with DeepSeekTo run it, follow these instructions:

1. Open the command prompt again.
2. Type the following command: ollama run deepseek-r1:8b.
3. DeepSeek will start and be ready to answer your questions. Type any message into the terminal and press Enter to get a response.

If you want to end the session, type /bye and you will be returned to the initial state of the command prompt. DeepSeek also features commands costs which you can consult by writing /?.

Alternative: Using LM Studio

If you prefer an experience with Graphic interface Instead of working from the terminal, LM Studio is a great alternative. This software allows you to load DeepSeek models visually and facilitates interaction.

• Download LM Studio from its official site.
• Install it by following the steps in the setup wizard.
• Open the program and search for the model DeepSeek R1 in your model finder.
• Download version 8B or the one you prefer based on your computer's capabilities.
• Load the model and start interacting with it through a chat-like visual interface.

This option eliminates the need to use commands, which is ideal for starters or less experienced users.

Installing DeepSeek locally on your computer is an excellent option if you value the privacy, as none of your data is shared with third parties. Plus, its ability to work offline makes it a versatile tool for any user, from students to developers. With options like Ollama or LM Studio, you have flexibility to choose the configuration that best suits your needs and knowledge.