How to use or disable Model Thinking in Ollama (Python Tutorial)

This tutorial covers how to enable or disable reasoning model thinking in Ollama for large language models (LLMs). This feature essentially allows you to prevent reasoning AI models such as DeepSeek-R1 or Qwen 3 from outputting their chain-of-thought (CoT) reasoning, which results it lower latency and higher speed.

The video covers the latest updates, how to install Ollama on your computer, how to run it locally, and how to turn thinking mode on or off.

If you find this helpful :
- **Like (👍)**
- Comment
- **Subscribe**

**Subscribe for FREE to the Deep Charts Newsletter**

**Resources**

**FULL CODE**

*Chapters*
0:00 Model Thinking in Ollama: What it is as well as different use cases for Chatbots vs Agentic AI systems
0:48 How to install the latest version of Ollama for your computer
1:12 How to install an Ollama reasoning model (example: Qwen3)
1:22 How to enable or disable Model Thinking for reasoning models in Ollama

[SonGoku-pcjl]

thanks! good and fast explication for this important thinks! ;)

[NickRobinson-rihu]

With Deepseek im finding thinking is still leaking through occasionally, any ideas?