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 run Llama-based models locally.
- 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.
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.
You've hit a Deep Dive tutorial.
I spend dozens of hours researching, coding, and breaking things to write these guides. This content is free, but reserved for my subscriber community. Drop your email below to unlock this guide (and all past/future deep dives):
Full content temporarily unavailable — refresh in a moment
Already a subscriber? Use the magic link from your last newsletter, or reset your password.
Log in to unlock
New subscribers get an inbox mail: Set a password to unlock articles. The form does not log you in — use the same email afterwards.
