Why Use DeepSeek R1 Offline?

Running DeepSeek R1 on your local machine has several advantages:

✔ Privacy: No internet required, keeping your data secure.
✔ Cost Savings: No need to pay for expensive cloud AI services.
✔ Speed: No delays caused by internet connectivity.
✔ Offline Access: Use AI anytime, anywhere.

Requirements

To run DeepSeek R1 smoothly, make sure your system meets these requirements:

1. Hardware Requirements

• RAM: At least 8GB (more for larger models).
• Storage: Minimum 10GB free space.
• CPU/GPU: A good processor is required. A dedicated GPU will improve performance.

2. Supported Operating Systems

• Windows
• macOS
• Linux

Step 1: Install Ollama

Ollama is the tool that lets you download and run AI models on your computer.

1. Download Ollama

Go to Ollama’s official website and download the installer for your operating system.

2. Install Ollama

• Windows: Double-click the downloaded .exe file and follow the installation steps.
• macOS: Open the .dmg file and drag Ollama into the Applications folder.
• Linux: Follow the commands given on the Ollama website for your distribution.

3. Verify Installation

After installation, open the Terminal (Mac/Linux) or Command Prompt (Windows) and type:

ollama list

If Ollama is installed correctly, this command will either list available models or show an empty list if no models are installed yet.

Step 2: Download the DeepSeek R1 Model

DeepSeek R1 is available in different sizes. Choose the one that fits your system best:

1. Download the Model

Open the Terminal or Command Prompt and type:

ollama run deepseek-r1:8b

(Replace 8b with 1.5b or 14b if you want a different version.)

This will download the DeepSeek R1 model. It may take a few minutes depending on your internet speed.

Step 3: Install Chatbox AI

Chatbox AI provides a user-friendly interface to interact with the AI model.

1. Download Chatbox AI

Visit Chatbox AI’s website and download the installer for your system.

2. Install Chatbox AI

• Windows: Run the .exe installer and follow the steps.
• macOS: Drag the downloaded file into the Applications folder.

• Linux: Follow the installation instructions on the website.

   

Step 4: Connect Chatbox AI to Ollama

Now, we need to make sure Chatbox AI can use the DeepSeek R1 model through Ollama.

1. Open Chatbox AI

Launch the Chatbox AI app on your computer.

2. Change the Settings

• Go to Settings in Chatbox AI.
• Select "Ollama" as the model provider.

• Enter the API Host as:

  http://127.0.0.1:11434

• Choose DeepSeek R1 (Make sure it matches the version you downloaded, e.g., deepseek-r1:8b).

3. Save Settings

Click Save to apply the changes.

Step 5: Start Ollama

Before using Chatbox AI, we need to start Ollama so it can handle AI requests.

1. Open the Terminal or Command Prompt

2. Run Ollama

Type this command to start the Ollama server:

ollama serve

Leave this terminal window open in the background while using Chatbox AI.

Step 6: Start Using DeepSeek R1

1. Open Chatbox AI

Launch the Chatbox AI app.

2. Ask Questions!

Start typing your questions or commands. DeepSeek R1 will process them and generate responses.

Additional Tips

1. Improve Performance

• Close other heavy applications to free up system resources.
• Use a smaller model if your computer is slow.

2. Run Ollama Automatically on Startup

• On macOS: Run this command to enable auto-start:

  launchctl setenv OLLAMA

• On Windows: Add ollama serve to your startup applications.

3. How to Update Ollama or Models

To update Ollama, run:

ollama update

To update DeepSeek R1, run:

ollama pull deepseek-r1:8b