All terms
Foundations
Small Language Model
A language model with far fewer parameters than a large model, built to run fast and cheap on modest hardware.
Definition
A small language model is a language model built with a fraction of the parameters of a frontier LLM — often a few hundred million to a few billion instead of hundreds of billions. That smaller size means faster responses, lower cost, and the ability to run on a phone, laptop, or other device with no data center required. SLMs typically trade away some general knowledge and reasoning breadth for that efficiency, so they work best when fine-tuned or prompted for a narrower task rather than asked to do everything an LLM can.