Install OpenThinker Large Language Model (LLM) on Windows – LLM Better than DeepSeek-R1

In this Large Language Model (LLM) tutorial, we explain how to install and run locally OpenThinker LLM on a Windows computer. OpenThinker is a family of LLMs that are obtained by the process of fine-tuning Qwen2.5 by using the OpenThoughts-114k dataset. The OpenThoughts-114k dataset consists of around 114,000 coding and puzzle problems and solutions. In this tutorial, we explain how to install and run locally OpenThinker by using Ollama, and by using Open WebUI to generate a Graphics User Interface (GUI). The YouTube tutorial is given below.

How to install OpenThinker Large Language Model on Windows

First of all, we need to install Ollama. To install Ollama, go to the Ollama website

https://www.ollama.com

and click on Download to download the Ollama installation file.

After the Ollama installation file is downloaded, click on it to install it. After installing Ollama. Open a Command Prompt and run a command for installing the OpenThinker model. OpenThinker comes in two flavors, a smaller 7B model and a larger 32B model. Depending on your hardware and computer resources, you should select the model. In our case, we were able to run both models on NVIDIA 3090 GPU with 24GB RAM. To download the smaller model type this

ollama pull openthinker:7b

To download the larger model, type this

ollama pull openthinker:32b

You can test these models in a terminal by typing this:

ollama run openthinker:7b

or

ollama run openthinker:32b

Then, the next step is to generate a GUI for running the model. To do that, open a command prompt and type

cd\
mkdir testWebUI
cd testWebUI

python -m venv env1
env1\Scripts\activate.bat

pip install open-webui
open-webui serve

This will start the Open-WebUI. To start the GUI, type in the web browser the following address

http://localhost:8080

For more details see the YouTube tutorial given above.

Additional Resources

• Ollama website of OpenThinker: https://ollama.com/library/openthinker
• HuggingFace repository of OpenThinker: https://huggingface.co/open-thoughts/OpenThinker-32B
• OpenThoughts-114k dataset: https://huggingface.co/datasets/open-thoughts/OpenThoughts-114k
• Open WebUI: https://github.com/open-webui/open-webui