Definition
A small language model (SLM) is a compact language model, typically with a few billion parameters or fewer, that runs on modest hardware and can be fine-tuned to perform well on narrow tasks.
Why small
Small models are cheaper to run, respond faster and fit on fewer GPUs, which matters for on-premise deployments and voice agents.
When they shine
Fine-tuned on a specific task, such as classification, extraction or a house style, a small model can match much larger general models on that task.