# What is a Large Language Model, really?

> A plain-language look at how LLMs work under the hood – tokens, context, and probabilities – without the jargon.

*Source: https://velstech.net/what-is-an-llm · Updated: 2026-08-24 · Category: AI · Tags: LLM, Basics*

*Markdown version of [What is a Large Language Model, really?](https://velstech.net/what-is-an-llm). [Read the full guide with interactive tools](https://velstech.net/what-is-an-llm).*
*Also as Markdown: [Hindi](https://velstech.net/what-is-an-llm.hi.md) · [Tamil](https://velstech.net/what-is-an-llm.ta.md).*

---

You've probably chatted with one – ChatGPT, Claude, Gemini. But when someone says
"large language model", what's actually inside? Here's a plain-language tour of the
machinery, without the jargon.

## Three words, unpacked

**Language model** – a program trained to predict the next word in a sequence.
That's it. Not to "think", not to "understand" in a human sense. It's a next-word machine.
Everything else is a consequence of doing that one job astonishingly well.

**Large** – the model has billions of adjustable numbers (parameters) and was
trained on a huge slice of the internet's text. That scale is what turns "predict the next
word" into something that can answer questions, write essays, and debug code.

## Tokens: the real alphabet

Models don't read letters or words directly – they read **tokens**. A token is a
chunk of text that's typically a few characters long. For example:

```
"VelsTech writes about tech"
  -> "Vels" | "Tech" | " writes" | " about" | " tech"
```

The model predicts one token at a time, and each predicted token is appended to the input
before predicting the next. That's why longer responses take longer: every word is a fresh
prediction.

## How it learns

During training, the model reads massive amounts of text and repeatedly tries to predict the
next token. When it's wrong, its internal numbers are nudged so it's slightly less wrong next
time. Repeat that a few trillion times and you get a model that has absorbed patterns of
grammar, facts, reasoning, and style – not because it memorized them, but because they're the
patterns that best predict text.

> A useful mental model: the LLM has learned the "shape" of human text – how concepts usually
> connect – and generates by following that shape.

## Context: what it "sees"

When you send a prompt, everything you write – plus everything the model has generated in the
same conversation – becomes the **context window**. The model only "knows" what's
in that window. It doesn't have a memory of previous chats, and it doesn't browse the live web
unless a tool tells it to.

That's why the same question can get different answers: the model isn't recalling "the" answer,
it's generating the most probable continuation given *your specific context*.

## Temperature: creativity dial

At each step the model doesn't pick just one next token – it assigns a probability to many and
samples from them. The **temperature** setting controls how random that sampling is:

- Low (0–0.3): predictable, deterministic answers. Great for code and math.

- Medium (0.7): balanced, natural conversation.

- High (1+): creative, varied, sometimes nonsensical. Good for brainstorming.

## Why it still gets things wrong

Because it's predicting text, not checking facts, an LLM can confidently produce statements that
are wrong – or entirely invented (often called a **hallucination**). It's not lying;
it's just being very smooth at writing something that *looks* right.

The practical takeaway: use LLMs as a fast first draft, a tutor, or a coding assistant – but
verify anything important before you trust it.

## Summary

A large language model is a next-word predictor. It is scaled up with billions of
parameters and trained on enormous amounts of text. Everything it does – writing,
reasoning, answering – emerges from that single, simple job.

🔧 Try the VelsTech LLM VRAM Calculator

Wondering how much GPU memory a model needs at your quantization and context length? Get a size + fit estimate in seconds.

[Open calculator →](https://velstech.net/llm-vram-calculator)

## FAQ

**Is a large language model the same as artificial intelligence?**

No. An LLM is one kind of AI – a model trained to predict the next word. 'AI' is a much bigger umbrella that includes vision, robotics, and more.

**Do LLMs actually understand what they're saying?**

They don't reason the way a human does. They compute the most likely next token based on patterns in their training data, which often looks a lot like understanding.

---

*VelsTech – technology explained for everyone. Original: https://velstech.net/what-is-an-llm*