DeepSeek R1 is an exciting AI model that you can run locally without relying on cloud services. In this guide, I’ll show you step-by-step how to set up and run DeepSeek R1 Distilled using Ollama and Open WebUI. By the end, you’ll have a fully functional local AI chatbot accessible via your web browser! If you are ready, then let’s get started! ;) How to Run DeepSeek R1 Distilled Locally The installation is pretty straightforward. We’ll need only four things: Docker
Ollama
Open WebUI
DeepSeek R1 Model Step 1: Install Docker First, we need to set up Docker. We would need it to run Open WebUI. 1.1 Download Docker Go to Docker’s official website.


Download Docker Desktop for your operating system (Windows, macOS, or Linux).


Follow the installation instructions for your OS. 1.2 Install Docker on Ubuntu (Linux Users) If you’re using Ubuntu, install Docker via the terminal: sudo apt-get update
sudo apt-get install ./docker-desktop-amd64.deb Once installed, confirm that Docker is working: docker --version Step 2: Install Ollama Ollama is a tool for running AI models locally. 2.1 Download Ollama Visit Ollama’s website.


Click the Download button.


Install Ollama on Windows, macOS, or Linux by following the instructions on the site. 2.2 Install Ollama on Linux (Ubuntu Example) For Ubuntu, install it with: curl -fsSL https://ollama.com/install.sh | sh Verify installation: ollama --version Step 3: Install Open WebUI Open WebUI provides a user-friendly chat interface for AI models. Install Open WebUI 3.1 Install Open WebUI with Docker Open your terminal.


Pull the Open WebUI Image. docker pull ghcr.io/open-webui/open-webui:main Wait for the installation to complete.


Run the following command: docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v ollama:/root/.ollama -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:ollama Open your browser, and go to:http://0.0.0.0:3000


Create an account, and log in. Step 4: Import DeepSeek R1 Model Now that Open WebUI is running, we need to import DeepSeek R1. 4.1 Open Model Settings In Open WebUI, go to Settings (bottom-left menu).


Click Admin Settings → Models. 4.2 Download the DeepSeek R1 Model Click Import Model (top-right button).


Open the Ollama models page.


Find DeepSeek R1 and copy the installation command.


Go back to Open WebUI and paste the command.


Remove the ollama run part, and keep only the model name.


Click Import, and wait for the download to complete (this can take a few minutes, depending on your internet speed). Start Chatting With DeepSeek R1 Once the model is imported, you’re ready to chat! First, refresh the Open WebUI page to ensure everything is loaded correctly. Then, click New Chat and select DeepSeek R1 from the available models. Now, type your first message and see how the AI responds! DeepSeek R1 offers some useful features beyond basic chatting. You can upload text files to the chat for analysis. It also supports PDF summarization, allowing you to extract key insights from documents. However, note that image support is limited at this time. If you experience any slow performance, try restarting your computer to refresh the system. Video Tutorial I’ve created a video for those who have trouble with written tutorials. https://youtu.be/7tkstNuCt8I?embedable=true Final Thoughts You now have DeepSeek R1 running locally and accessible via your web browser! 🎉 This setup lets you use an AI chatbot without sending data to the cloud. If you found this tutorial helpful, like, subscribe, and share your experience in the comments. Cheers! DeepSeek R1 is an exciting AI model that you can run locally without relying on cloud services. In this guide, I’ll show you step-by-step how to set up and run DeepSeek R1 Distilled using Ollama and Open WebUI . By the end, you’ll have a fully functional local AI chatbot accessible via your web browser! If you are ready, then let’s get started! ;) DeepSeek R1 DeepSeek R1 DeepSeek R1 Distilled Ollama Open WebUI local AI chatbot How to Run DeepSeek R1 Distilled Locally The installation is pretty straightforward. We’ll need only four things: Docker Ollama Open WebUI DeepSeek R1 Model Docker Ollama Open WebUI DeepSeek R1 Model Step 1: Install Docker First, we need to set up Docker. We would need it to run Open WebUI. 1.1 Download Docker Go to Docker’s official website. Download Docker Desktop for your operating system (Windows, macOS, or Linux). Follow the installation instructions for your OS. Go to Docker’s official website. Go to Docker’s official website . Docker’s official website Docker’s official website Download Docker Desktop for your operating system (Windows, macOS, or Linux). Download Docker Desktop for your operating system (Windows, macOS, or Linux). Docker Desktop Follow the installation instructions for your OS. Follow the installation instructions for your OS. 1.2 Install Docker on Ubuntu (Linux Users) If you’re using Ubuntu , install Docker via the terminal: Ubuntu sudo apt-get update
sudo apt-get install ./docker-desktop-amd64.deb sudo apt-get update
sudo apt-get install ./docker-desktop-amd64.deb Once installed, confirm that Docker is working: docker --version docker --version Step 2: Install Ollama Ollama is a tool for running AI models locally. 2.1 Download Ollama Visit Ollama’s website. Click the Download button. Install Ollama on Windows, macOS, or Linux by following the instructions on the site. Visit Ollama’s website. Visit Ollama’s website. website . website Click the Download button. Click the Download button. Download Install Ollama on Windows, macOS, or Linux by following the instructions on the site. Install Ollama on Windows, macOS, or Linux by following the instructions on the site. Windows, macOS, or Linux 2.2 Install Ollama on Linux (Ubuntu Example) For Ubuntu , install it with: Ubuntu curl -fsSL https://ollama.com/install.sh | sh curl -fsSL https://ollama.com/install.sh | sh Verify installation: ollama --version ollama --version Step 3: Install Open WebUI Open WebUI provides a user-friendly chat interface for AI models. Open WebUI Open WebUI Install Open WebUI 3.1 Install Open WebUI with Docker Open your terminal. Pull the Open WebUI Image. Open your terminal. Open your terminal . terminal Pull the Open WebUI Image. Pull the Open WebUI Image. docker pull ghcr.io/open-webui/open-webui:main docker pull ghcr.io/open-webui/open-webui:main Wait for the installation to complete. Run the following command: Wait for the installation to complete. Wait for the installation to complete. Run the following command: Run the following command: docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v ollama:/root/.ollama -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:ollama docker run -d -p 3000:8080 --add-host=host.docker.internal:host-gateway -v ollama:/root/.ollama -v open-webui:/app/backend/data --name open-webui --restart always ghcr.io/open-webui/open-webui:ollama Open your browser, and go to:http://0.0.0.0:3000 Create an account, and log in. Open your browser, and go to:http://0.0.0.0:3000 Open your browser, and go to: http://0.0.0.0:3000 http://0.0.0.0:3000 Create an account, and log in. Create an account, and log in. Step 4: Import DeepSeek R1 Model Now that Open WebUI is running, we need to import DeepSeek R1 . DeepSeek R1 4.1 Open Model Settings In Open WebUI, go to Settings (bottom-left menu). Click Admin Settings → Models. In Open WebUI, go to Settings (bottom-left menu). In Open WebUI, go to Settings (bottom-left menu). Settings Click Admin Settings → Models. Click Admin Settings → Models . Admin Settings Models 4.2 Download the DeepSeek R1 Model Click Import Model (top-right button). Open the Ollama models page. Find DeepSeek R1 and copy the installation command. Go back to Open WebUI and paste the command. Remove the ollama run part, and keep only the model name. Click Import, and wait for the download to complete (this can take a few minutes, depending on your internet speed). Click Import Model (top-right button). Click Import Model (top-right button). Import Model Open the Ollama models page. Open the Ollama models page. Find DeepSeek R1 and copy the installation command. Find DeepSeek R1 and copy the installation command. DeepSeek R1 Go back to Open WebUI and paste the command. Go back to Open WebUI and paste the command . paste the command Remove the ollama run part, and keep only the model name. Remove the ollama run part, and keep only the model name. ollama run Click Import, and wait for the download to complete (this can take a few minutes, depending on your internet speed). Click Import, and wait for the download to complete (this can take a few minutes, depending on your internet speed). Import, Start Chatting With DeepSeek R1 Once the model is imported, you’re ready to chat! First, refresh the Open WebUI page to ensure everything is loaded correctly. Then, click New Chat and select DeepSeek R1 from the available models. Now, type your first message and see how the AI responds! DeepSeek R1 offers some useful features beyond basic chatting. You can upload text files to the chat for analysis. It also supports PDF summarization, allowing you to extract key insights from documents. However, note that image support is limited at this time. If you experience any slow performance, try restarting your computer to refresh the system. Video Tutorial I’ve created a video for those who have trouble with written tutorials. https://youtu.be/7tkstNuCt8I?embedable=true https://youtu.be/7tkstNuCt8I?embedable=true Final Thoughts You now have DeepSeek R1 running locally and accessible via your web browser! 🎉 This setup lets you use an AI chatbot without sending data to the cloud. If you found this tutorial helpful, like, subscribe, and share your experience in the comments. Cheers!

How to Obsidian Sync for FREE! (No Paid Plan Required)

Turn Obsidian Into an AI-Powered Second Brain With DeepSeek-R1 Model

Read My Blog

Read My Stories

Too Long; Didn't Read

Make resilience your competitive advantage

Ollama DeepSeek R1: Run Locally (Web Interface)

About Author

Comments

TOPICS

THIS ARTICLE WAS FEATURED IN

Related Stories

Untitled Story

How to Remove Invisible Characters From AI Text (Free Tool)

How the USA Could Beat China in the AI Race (Hint: It Doesn't)

DeepSeek Releases Cheapest Ever LLM In The World

When the East Out-Codes the West: The Hottest AI Race You Can’t Miss: DeepSeek & ChatGPT

Run DeepSeek R1 Locally to Learn How It 'Thinks'—Here's How

How to Remove Invisible Characters From AI Text (Free Tool)

How the USA Could Beat China in the AI Race (Hint: It Doesn't)

DeepSeek Releases Cheapest Ever LLM In The World

When the East Out-Codes the West: The Hottest AI Race You Can’t Miss: DeepSeek & ChatGPT

Run DeepSeek R1 Locally to Learn How It 'Thinks'—Here's How

Light-Mode

Classic

Newspaper

Dark-Mode

Neon Noir

Minty

HN StartUps