Local LLMs with Ollama for Absolute Beginners

This course contains the use of artificial intelligence.

Local AI is the next frontier

• The organisations that move first on private, local AI will have a significant competitive edge. This course gives you the knowledge and hands-on skills to lead that adoption in your team or organisation: reduced cloud costs, no data privacy risks

• The job market is already shifting. Roles in AI operations, IT infrastructure, and enterprise automation are increasingly asking for experience with local model deployment, self-hosted AI tools, and private LLM workflows.

  
  

  ** Getting ahead of the Local AI wave now is a massive career advantage **

We start with a concise introduction to Generative AI and Large Language Models — just enough theory to understand what you're working with. Then we get hands‑on immediately: you'll install Ollama, run real open-source models like Llama, Mistral and DeepSeek on your own machine, and use Open WebUI as your private, local "ChatGPT-style" interface.

A dedicated section then covers prompting local models effectively — because smaller, local LLMs behave differently from ChatGPT and Claude, and knowing how to get reliable outputs from them is a real skill. You'll learn prompt patterns, prompting techniques, and how to design prompts that work consistently across different local models.

Finally, for those who want to go further, an advanced section walks you through connecting your local models to self‑hosted n8n — so you can build private AI automations. Note: this section involves Docker and self‑hosted software setup and is aimed at learners comfortable going beyond basic installations.

By the end of this course, you will be able to:

• Confidently introduce and advocate for local AI tools within your team or organisation

• Explain what Generative AI and LLMs are, and why running them locally matters for privacy and cost.

• Install and use Ollama to run popular open‑source models (Llama, Mistral, DeepSeek) on your own machine.

• Choose the right local model for your task based on size, speed and capability.

• Use Open WebUI as a powerful, private ChatGPT‑style interface over your local models.

• Prompt local LLMs effectively — understanding how smaller models behave differently from cloud AI and how to get reliable outputs from them.

• (Advanced) Set up self‑hosted n8n on Docker  and connect it to your local LLMs to build private automations and simple AI agents