What Is a "Model"?

Part of the Fundamentals section of Coddy's AI Prompts journey — lesson 6 of 23.

You've been chatting with "an AI," but you're really talking to a model — a specific AI system trained on data to generate responses.

"AI" is the general concept; a "model" is a particular version you can actually use. Common ones include GPT-4, Claude, Gemini, and Llama, each built by different companies.

The same prompt can produce very different results depending on the model.

What Are Parameters?

A model's size is measured in parameters — numbers it learned during training that shape how it responds.

More parameters generally means more capability, but also more computing power needed to run it.

GPT-4 has an estimated trillion+ parameters. On this site, we use Qwen3 0.6B — just 600 million. That's intentionally small.

Large models need expensive GPUs and lots of memory; a 0.6B model can run on a regular laptop.

The tradeoff is less power on complex tasks — but it's perfect for learning prompt engineering. If you can get good results from a small model, your prompts will work even better on larger ones.

Cheat sheet

An AI model is a specific AI system trained on data to generate responses. Common models include GPT-4, Claude, Gemini, and Llama.

A model's size is measured in parameters — numbers learned during training that shape responses. More parameters generally means more capability, but also more computing power needed.

Small models (like 0.6B parameters) can run on regular laptops, while large models (like GPT-4 with trillion+ parameters) need expensive GPUs. Prompts that work well on small models will work even better on larger ones.

Try it yourself

This lesson doesn't include a code challenge.