Running DeepSeek R1 Locally with Ollama: Overview

Ollama is an open-source runtime that downloads and runs large language models locally from a single command line, and DeepSeek R1 is an open-source reasoning model whose distilled variants match OpenAI-o1-class performance. Large Language Models (LLMs) are becoming more popular, especially as people want to run AI tools on their devices. Running a model locally protects your privacy, reduces wait times, and lowers costs.

Two tools making this possible are:

• Ollama: A command-line tool to download and run open-source LLMs locally (Llama, DeepSeek, Mistral, and more).
• DeepSeek R1: An open-source reasoning language model from the Chinese company DeepSeek that’s gaining attention quickly.

What is DeepSeek R1, and is it better than ChatGPT and other AI models?

According to a TechCrunch article by Maxwell Zeff, DeepSeek has surpassed popular AI models like ChatGPT in downloads and usage, thanks to its open models that compete at a lower cost. The app has seen over 300% more downloads than Perplexity in just a week [1]!

So the open source models of DeepSeek become very interesting to investigate and try out for me, as a notorious GPT user :)

This post will explore how to use Ollama and DeepSeek R1 together. We’ll walk through their installation and basic usage.

I will surely use Ollama to download and run the DeepSeek R1 model and briefly compare it with the Llama3.2 model.

What Is Ollama?

Ollama is an open-source app that allows you to run large language models like Llama on your own machine.

It provides:

• Local Inference: Your data stays on your machine when you run the model.
• Command-Line Interface: Easily interact with the model directly from your terminal.
• Easy Model Management: Simple downloads and updates for different language models.

Ollama aims to make experimenting with LLMs easy without needing cloud services.

Installing Ollama

To install Ollama:

1. Visit the Download Ollama page or the Ollama GitHub.
2. Download the latest installer for your platform.
3. Open the installer and follow the on-screen instructions.

You can check if Ollama is installed successfully by running the command:

ollama -v

It should display Ollama’s version:

ollama version is 0.5.7

Using Homebrew

If you prefer using Homebrew, ensure you have it installed.

You can use the following command to install Homebrew with curl:

   /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)"

Then, install Ollama with this command:

   brew install ollama

Update: Homebrew used to require the ollama/tap/ollama tap; Ollama now ships as a core Homebrew formula, so a plain brew install ollama is all you need. Once the installation completes, verify:

   ollama version

Downloading DeepSeek R1 with Ollama (ollama pull deepseek-r1)

Running DeepSeek R1 with Ollama starts with finding the model: on the Ollama website, you can search for many models, including DeepSeek, or browse every tag directly on the official DeepSeek R1 model library page.

Update: when this post was first written, the untagged deepseek-r1 name pulled the smallest 1.5b variant by default. That’s no longer true — Ollama has since re-pointed the untagged tag to the DeepSeek-R1-0528-Qwen3-8B checkpoint (a mid-2025 refresh of R1), so a bare ollama pull deepseek-r1 today gets you the 8b model, not 1.5b. If you specifically want the smallest model, tag it explicitly, as we do below — ollama run pulls the model automatically if you don’t have it yet:

ollama run deepseek-r1:1.5b

pulling manifest 
pulling aabd4debf0c8... 100% ▕████████████████▏ 1.1 GB                         
pulling 369ca498f347... 100% ▕████████████████▏  387 B                         
pulling 6e4c38e1172f... 100% ▕████████████████▏ 1.1 KB                         
pulling f4d24e9138dd... 100% ▕████████████████▏  148 B                         
pulling a85fe2a2e58e... 100% ▕████████████████▏  487 B                         
verifying sha256 digest 
writing manifest 
success 

Managing other models, the model sizes, the background on DeepSeek R1 and the comparison with Llama 3.2 follow below.

What Is DeepSeek R1?

🔒 Subscribe to keep reading.

Prompting DeepSeek R1: CLI, Files, and Python

🔒 Subscribe to keep reading.

Conclusion

🔒 Subscribe to keep reading.

References

🔒 Subscribe to keep reading.