← Concept IndexDEFINITION WHY IT MATTERS COMMONLY CONFUSED WITH
Model size and capability
Also called: small vs large models, parameter count, right-sizing
Larger models (more parameters) tend to be more capable but slower and costlier to run; smaller models are faster and cheaper and are often good enough — or better — for a specific, narrow task.
Reaching for the biggest model by default wastes money and latency. Matching model size to the task is one of the main levers for making an AI feature affordable and responsive at real volume.
Bigger always being better. On a narrow, well-defined task a small model can match a large one at a fraction of the cost — which only your own evaluation will reveal.