Learning Generative AI

Deploying Free LLM APIs Offline on Your Local Machine

Explore LLM Development Without Relying on Paid ChatGPT Services

Photo by Zulfugar Karimov on Unsplash

I wanted to dive into building applications with LLMs — but every service I found asked for a credit card before I could even get started. If you’re in the same boat, this article is for you. I’ll walk you through how I set up my own local LLM service — no internet, no subscription — and how I’m now free to experiment application development with LLM.

This article is the second part of my previous article below, where I previously share how we can have LLM run locally on the console, and Web UI.

Running LLM on a Local Mac Machine

In this article, I’ll share using the LLM as an locally served API, and linked it on your application development (several Python example below).

1. Starting Your Local LLM Server

The prior article shows you how you can download the Serving Engine, Ollama, and run it on LLM model like Meta’s LLaMa 3. To…