Parameters

In one sentenceThe billions of internal settings a model learns during training. More parameters usually means more capability, and more cost.

What it means

Parameters are the numbers inside a model that get adjusted during training. Together they store everything the model learned about language and the world.

You will see model sizes described like "8B" or "70B" (8 billion or 70 billion parameters). Bigger models tend to be smarter but slower and more expensive to run.

How to use it

• You rarely need to think about this as a user. It matters when choosing a model for a product or running one on your own computer.
• Do not confuse parameters with settings you control, like Temperature.

Related terms

Model LLM Open-Weight Model