1. Self-Hosted AI: the LLM concepts you need to run models effectively
If you want to run AI models on your own machine and learn the basic concepts with me to do it effectively, then this is the right article :). This is part one of the series. In the next one we build local AI workflows with n8n and Ollama. This article is the vocabulary we need to pick a model, load it without crashing your machine, and know what each setting does. The pieces Running a model locally involves a few separate things that people mix up all the time. The model is a file on your disk. The server (Ollama, LM Studio) loads that file and runs the math. The API is a local address the server opens so other apps can reach it. The clients are whatever you point at it: a chat window, your code editor, an n8n workflow. You never talk to the model directly, you always go through the server. Model and inference The models we run are large language models (LLMs): machine learning models trained on massive text datasets to understand and generate language, built on a neural network type called a transformer[ Cloudflare ]. In practice a model is a file of learned numbers, called weights, and it works by predicting the next chunk of text over and over. Running a trained model to get answers is called inference, the step we do on our hardware, as opposed to training, which is how the model was built[ Cloudflare ]. Everything below is about making inference run well. Server and API The server loads and runs the model, and it opens a local API. An API is a set of rules that lets two pieces of software communicate [ AWS ]. Here it means an address on your own machine that apps send prompts to: Ollama: http://localhost:11434 LM Studio: http://localhost:1234 localhost means the request never leaves your computer. Both servers copy the OpenAI API format, so any tool built for ChatGPT's API can point at this address and work without changes. One running model can feed your editor, a chat app, and an n8n workflow at the same time. GPU, VRAM, and RAM This trio decides whether a m