How to Install DeepSeek R1 Locally on Your Computer

Want to run DeepSeek AI locally without sharing data online? With DeepSeek R1 and Ollama, you can install and use a powerful AI directly on your computer - completely offline. Give it a try, it's an exciting model ;)

Share
How to Install DeepSeek R1 Locally on Your Computer

Install Ollama to Run AI Locally

To use DeepSeek R1 without internet, you first need to install the tool Ollama. This makes it possible to run AI models directly on your computer instead of depending on cloud services. Ollama can also run many other great AI models and is definitely a favorite in our toolbox. Another perk is that you can reach it via localhost on port 11434, making it easy to call from other applications ;)

After installing, check that Ollama is running - it should show up as an icon at the bottom of your taskbar among the other icons.

Install the DeepSeek R1 AI Model

The next step is to install the DeepSeek R1 model. To make sure your computer can handle running the AI, it's best to choose a lighter version first, like the 1.5B model (1.5 billion parameters). We tried the largest model on a laptop with 64 GB of RAM and an Nvidia 4070 card. It ran very slowly and ate up most of the resources.

Here's a list of other DeepSeek models
1.5B version (smallest):

ollama run deepseek-r1:1.5b

8B version:
ollama run deepseek-r1:8b

14B version:
ollama run deepseek-r1:14b

32B version:
ollama run deepseek-r1:32b

70B version (largest/smartest):
ollama run deepseek-r1:70b

How to Install the Model

Open the terminal on your operating system, e.g. type cmd in the search field on Windows.

Enter the following command and press

ollama run deepseek-r1:1.5b

The installation begins, and once it's done, the AI is ready to use.

If you need a more powerful model, you can, for example, install the 32B version with:

Send an Instruction to the AI

Once the installation is complete, you can test the AI by typing a question in the command terminal. Feel free to ask about China ;)

Run the AI Model Offline

One of the benefits of running DeepSeek R1 locally is that the AI doesn't leak information. You can test this by disconnecting your computer from Wi-Fi/Ethernet - you'll still be able to run the model.

Stop and Exit DeepSeek in Ollama

To fully end the AI session, enter the command:

Useful Ollama Commands

You should know the commands below for loading and removing models. For example, to remove DeepSeek, type:

ollama rm deepseek-r1:1.5b

ollama serve: Starts the Ollama server on your local machine.

ollama create <model-name> -f <Modelfile>: Creates a new model based on a specified Modelfile.

ollama show <model-name>: Shows detailed information about a specific model, including its configuration and parameters.

ollama run <model-name>: Runs the specified model and opens an interactive session for user interaction.

ollama pull <model-name>: Downloads the specified model to your system.

ollama list: Shows a list of all models currently downloaded on your system.

ollama ps: Shows a list of all models currently running.

ollama stop <model-name>: Stops a specific model that's currently running.

ollama rm <model-name>: Removes the specified model from your system.

ollama help: Provides help and information about available commands and their usage.

More Models to Download for Ollama