How to Install DeepSeek Locally on Ubuntu 24.04 – A Step-by-Step Guide
DeepSeek is a powerful open-source AI model perfect for natural language processing and text generation. In this guide, we’ll walk you through installing DeepSeek locally on your Ubuntu 24.04 system—no cloud services required. We’ll even show you how to add a handy web interface to make it easier to use. Whether you’re into privacy, Monero, or exploring cashless tech solutions, this setup keeps your data in your control. Let’s dive in!
Why Install DeepSeek Locally?
Running DeepSeek on your own machine offers some big wins:
- Privacy: Your data stays on your device—no third-party servers involved.
- Control: Customize the model to fit your needs, from Monero research to privacy tools.
- Offline Power: Once installed, it works without an internet connection.
For developers, researchers, or privacy buffs who want cutting-edge AI on their terms, DeepSeek is a fantastic choice.
What You’ll Need to Get Started
Before we begin, make sure your system meets these requirements:
- Operating System: Ubuntu 24.04.
- RAM: At least 8 GB (16 GB or more recommended).
- Disk Space: Enough free space for the model (e.g., the 7B model takes about 4.7 GB).
- Internet: Needed during setup for downloads.
Step 1: Update Your Ubuntu System
First, let’s ensure your system is up to date. Open a terminal and run these commands:
sudo apt update
sudo apt upgrade -y
These will fetch and install the latest updates for Ubuntu 24.04.
Step 2: Install Python and Git
DeepSeek requires Python (version 3.8 or higher) and Git. Ubuntu 24.04 usually has a recent Python version by default. Install them with:
sudo apt install python3 python3-pip git -y
Check they’re working:
python3 --version
git --version
If you see version numbers, you’re good to go!
Step 3: Install Ollama
Ollama is a platform that makes running large language models like DeepSeek a breeze. Install it with this command:
curl -fsSL https://ollama.com/install.sh | sh
Verify it worked:
ollama --version
Start Ollama and set it to launch automatically:
sudo systemctl start ollama
sudo systemctl enable ollama
Step 4: Download the DeepSeek Model
Now, let’s grab DeepSeek. We’ll use the R1-7B model in this example (about 4.7 GB). Run:
ollama run deepseek-r1:7b
The download might take a bit depending on your internet speed. Once it’s done, you can test it right in the terminal by typing questions or commands.
To see available models, use:
ollama list
Step 5: Add a Web Interface (Optional)
Want to use DeepSeek through your browser? Install the Open WebUI for a sleek, visual experience.
Set up a Python virtual environment:
sudo apt install python3-venv -y
python3 -m venv ~/open-webui-venv
source ~/open-webui-venv/bin/activate
Install Open WebUI:
While the virtual environment is active, run:
pip install open-webui
Launch it:
open-webui serve
Open your browser and go to http://localhost:8080. Create an admin account, select the DeepSeek model from the dropdown, and start exploring!
Make WebUI Auto-Start (Optional):
Set up a systemd service:
sudo nano /etc/systemd/system/open-webui.service
Add this (replace your-username with your actual username):
[Unit]
Description=Open WebUI Service
After=network.target
[Service]
User=your-username
WorkingDirectory=/home/your-username/open-webui-venv
ExecStart=/home/your-username/open-webui-venv/bin/open-webui serve
Restart=always
Environment="PATH=/home/your-username/open-webui-venv/bin:/usr/local/sbin:/usr/local/bin:/usr/sbin:/usr/bin:/sbin:/bin"
[Install]
WantedBy=multi-user.target
Save and exit (Ctrl+O, Enter, Ctrl+X). Activate it:
sudo systemctl daemon-reload
sudo systemctl enable open-webui
sudo systemctl start open-webui
Wrapping Up
Congrats! You’ve installed DeepSeek on Ubuntu 24.04 and can use it via terminal or browser. This setup gives you full control over a powerful AI tool—perfect for digging into Monero, privacy solutions, or cashless innovations. Experiment with different models and features; the possibilities are endless!
Got questions or thoughts? Drop them in the comments below. Share this guide with fellow privacy and tech enthusiasts!