Review Generative AI DeepSeek-R1 32B Model

Live stream set for 2025-10-08 at 14:00:00 Eastern

Ask questions in the live chat about any programming or lifestyle topic.

This livestream will be on YouTube or you can watch below.

How to Run Ollama with DeepSeek-R1 32B LLM on Fedora 42 – Open Source AI for Everyone

Introduction

In this post, we will walk through the steps to get Ollama running on your system, with a special focus on using the DeepSeek-R1 32B LLM. This open-source model offers an impressive combination of text generation and deep learning power, and it is easy to integrate into your own projects. Whether you are a beginner or a seasoned developer, you will be able to follow along.

This guide includes step-by-step instructions for installing the necessary dependencies on Fedora 42, along with an example Python script that interacts with the Ollama API to run the DeepSeek-R1 32B model.

What is Ollama and DeepSeek-R1 32B?

Ollama is a platform designed for running and interacting with various AI models locally. It is open-source and highly flexible, making it perfect for running Large Language Models (LLMs) like DeepSeek-R1 32B.

• DeepSeek-R1 32B is a powerful 32 billion parameter language model that can be used for tasks like natural language generation, question answering, summarization, and more.
• Open Source License: DeepSeek-R1 is released under the MIT License, which means you can use, modify, and distribute it freely.

Installation Guide for Fedora 42

Step 1: Install Dependencies

To get started, install Ollama and the required dependencies:

# Install Python 3 and pip
sudo dnf install python3 python3-pip

# Install other necessary tools
sudo dnf install git curl

# Install the Ollama client
pip install ollama

Fedora 42 includes Ollama in the official repositories. You can install it easily using the system package manager.

# 1. Update your system
sudo dnf update -y

# 2. Install Ollama
sudo dnf install -y ollama

# 3. Start the Ollama service
ollama serve &

Ollama makes it incredibly simple to run LLMs locally with minimal setup, providing an intuitive CLI and REST API to interact with models like Meta’s LLaMA.

Step 2: Install DeepSeek-R1 32B Model

Download and set up the model locally:

ollama pull deepseek-r1:32b

Step 3: Increase System Swap Space (If Needed)

To prevent memory errors, increase swap space:

# Check current swap space
swapon --show

# Increase swap size by 4GB
sudo dd if=/dev/zero of=/swapfile bs=1M count=4096
sudo mkswap /swapfile
sudo swapon /swapfile

Using the Ollama API with Python

Below is a sample Python script that sends a prompt to the Ollama API and displays the response:

import requests

def ask_ollama(prompt):
    url = "http://localhost:11434/api/generate"
    payload = {
        "model": "deepseek-r1:32b",
        "prompt": prompt
    }
    
    response = requests.post(url, json=payload)
    
    try:
        return response.json()["response"]
    except Exception as e:
        print(f"Error: {e}")
        return None

if __name__ == "__main__":
    question = "What is the capital of Canada?"
    answer = ask_ollama(question)
    
    if answer:
        print("Answer:", answer)
    else:
        print("No answer returned.")

Explanation

This script sends a prompt to the local Ollama server using the DeepSeek-R1 32B model. It handles basic error checking and prints the model’s response.

Screenshots and Screencast

Here’s where you’ll find a visual walkthrough of setting up DeepSeek-R1 32B using Alpaca Ollama on your local system:

Results:

Who is the mayor of Toronto?

Produced inaccurate outdated answer to Olivia Chow as the mayor of Toronto.

I need a PHP code snippet to connect to a MySQL database.

Produced correct syntax PHP code snippet to connect to a MySQL database.

I need a 1080p screenshot of the gnome desktop environment.

Accurately provided instructions to generate a 1080p screenshot of Gnome desktop environment because it is a text-based AI lacking ability.

I need a kotlin code snippet to open the camera using Camera2 API and place the camera view on a TextureView.

Produced untested Kotlin code snippet.

I need a blender blend file for fire animation.

Accurately detected inability to generate Blender Blend file for a fire animation because it is a text-based AI lacking ability.

Results

Once you run the Python script, you should see output like this:

Answer: The capital of Canada is Ottawa.

This confirms that the DeepSeek-R1 32B model is working and responding correctly.

Additional Resources

• Book: Learning Python for Beginners
• Course: Learning Python Online Course
• One-on-One Tutorials: I offer personal Python tutoring. Contact me here.
• Model Installation & Custom Training: I can install DeepSeek-R1 32B or help train and migrate models. Hire me here.

Conclusion

Running DeepSeek-R1 32B with Ollama on Fedora 42 is possible and powerful. With just a few steps, you can start using advanced LLMs for local development, learning, or production use.

Whether you are writing a book, building an app, or training models, this setup puts full control in your hands.