Keeping Things Local - Making Your Own Private LLM

Have you ever wanted your own private version of ChatGPT, running securely on your own devices? While large language models (LLMs) can do amazing things, many users hesitate to send their sensitive files and data to companies like Microsoft, OpenAI, or Anthropic for processing. The good news is that it’s possible to set up your own local, controlled LLM using open-source tools, ensuring both privacy and flexibility. This talk will show you how to take advantage of these tools, guiding you through every step of the process.

We’ll start by covering the basics of installation, from choosing the right open-source LLM for your needs to setting it up on your system. Next, you’ll learn how to customize and optimize your model, ensuring it delivers the best results for your specific tasks and requirements. Whether you need it to help with coding, content creation, or data analysis, you’ll gain insights on how to tailor the LLM to meet your goals. Throughout the presentation, we’ll provide clear, easy-to-follow demos that break down each part of the setup, so you can see exactly how it all comes together.

By the end of this session, you’ll have the knowledge to create your own “mini-Jarvis,” ready to assist you with a range of tasks—all while keeping your data securely under your control. No more relying on third-party servers or worrying about privacy; instead, you’ll have a powerful, local AI that you can customize and manage as you see fit. Join us to discover how you can harness the potential of LLMs on your own terms, using open-source solutions to build a smart, effective, and private tool that truly works for you.