# GoLab: Ultimate Local AI

> A hands-on workshop on running local LLM inference in Go with Kronk — no cloud APIs, no data leaving your machine, and full GPU acceleration.

- Date: November 1st, 2026
- Time: 9:30AM – 3:30PM GMT+2
- Location: Bologna, Italy
- Instructor: Bill Kennedy
- Type: Workshop
- Register: https://golab.io/talks/ultimate-local-ai
- URL: https://www.ardanlabs.com/events/ultimate-local-ai-golab/

Running inference against LLM models on your own local hardware means no API costs, no data leaving your machine, and no vendor lock-in. In this workshop, Bill will introduce **Kronk**, a Go SDK that lets you embed local model inference directly into your Go applications with full GPU acceleration — **no CGO required**.

Whether you are building chat, vision, audio, embedding, or tool calling applications, Kronk gives you the same power as a model server without needing one. You will see live demos from writing your first chat app to driving a coding agent with a local model.

With that solid foundation, you'll build real applications:

- Retrieval-Augmented Generation (RAG) pipelines that ground model responses in your own documents using embeddings and vector search.
- Natural language-to-SQL systems where the model generates database queries from plain English, with grammar constraints ensuring the output is always valid executable SQL.

By the end of the day, you'll have built applications that load models, cache intelligently, retrieve context, and generate code — all running locally on your own hardware.

* * *

<div class="py-8">
  <div class="bg-primary/5 border-2 border-primary rounded-xl shadow-lg px-6 pb-6 mb-4">
    <h3 class="font-bold text-primary text-lg m-0">Hardware Requirements</h3>
    <p class="mb-2">Don't worry if you don't have the full hardware required for this. The instructor will provide everything you need to follow along and be able to run the examples.</p>
    <ul class="list-disc list-inside space-y-1">
      <li>Mac M1+ series with at least 16 GB RAM.</li>
      <li>Any Linux/Windows laptop with a dedicated GPU with at least 8GB VRAM (not system RAM) (pref 16GB).</li>
      <li>Access to a cloud-based instance with a dedicated GPU with at least 8GB VRAM (pref 16GB).</li>
    </ul>
  </div>
  <div class="bg-secondary/5 border-2 border-secondary rounded-xl shadow-lg px-6 pb-6 mb-4">
    <h3 class="font-bold text-secondary text-lg m-0">Prerequisites</h3>
    <p class="mb-2">It's expected that you will have been coding in Go for several months.</p>
    <p class="mb-0 mt-0">A working Go environment running on the device you will be bringing to class.</p>
  </div>
  <div class="bg-success/5 border-2 border-success rounded-xl shadow-lg px-6 pb-6 mb-4">
    <h3 class="font-bold text-success text-lg m-0">Recommended Preparation</h3>
    <p class="mb-2 mt-0">Please clone the main repo (<a href="https://github.com/ardanlabs/kronk" class="link link-hover font-bold text-success underline" target="_blank" rel="noopener noreferrer">https://github.com/ardanlabs/kronk</a>) for the class.</p>
    <p class="mb-2 mt-0">Please read the notes in the makefile for installing all the tooling and testing the code before class.</p>
    <p class="mb-0 mt-0">Please email the instructor, Bill Kennedy, for assistance.</p>
  </div>
</div>