Definition
A language model deliberately kept smaller than contemporary large models to reduce resource needs or fit a narrower deployment target.
Distinguish it from nearby terms
There is no permanent parameter threshold separating an SLM from an LLM. The term is relative to the current model landscape and the deployment's memory, latency, cost, and capability requirements.
Check your understanding
A smaller model can be the better production choice when it meets the task's quality bar with lower cost, latency, or exposure.