Book a call

Daniel & Friends / Glossary / Small language model (SLM)

AI and automation

Small language model (SLM)

A small language model (SLM) is a language model with far fewer parameters than the largest systems. It runs faster and cheaper, often even on a laptop or phone. For narrow tasks such as sorting messages it is often enough.

Daniel Votruba ·


In practice

Consider it where cost, speed or keeping data on the device matters. For broad and demanding tasks, reach for a large model.

Related terms

  • Large language model (LLM): A large language model is a model trained on a huge amount of text that predicts the next words and can write, summarise and answer.
  • Open-weight model: An open-weight model is a model whose trained weights you can download and run on your own infrastructure.
  • Inference and latency: Inference is the running of a finished model: it takes your input and produces an answer.
  • Foundation model: A foundation model is a large model pre-trained on a huge amount of data that serves as the base for many different tasks.

More terms in the group AI and automation

Speech-to-text · Shadow AI · System prompt · Semantic search · Temperature · RPA (robotic process automation) · Text-to-image · Reasoning model · Text-to-speech (TTS) · RAG (retrieval-augmented generation) · Text-to-video · Prompt injection · Token · Prompt engineering · Vector database · Prompt · Vibe coding · Predictive analytics · Voice cloning · Agentic AI · No-code and low-code · AI agent · NLP (natural language processing) · AI automation

Full glossary (590 terms)

Terms in practice

Need help putting them to work?

Terms are one thing, putting them to work is another. We go through which of them pay off for you and say so plainly. You get a first opinion for free and we reply within 24 hours.

Book a call

Enjoyed the article? Share it with friends.