Small Language Model
A language model with 1-4 billion parameters designed for efficient deployment on edge devices, offering lower costs and faster inference than frontier LLMs.
Small language models (SLMs) are neural networks with 1-4 billion parameters that can run efficiently on consumer hardware, edge devices, and local infrastructure. While less capable than frontier models on general tasks, fine-tuned SLMs often outperform larger models on domain-specific applications. The reduced parameter count enables deployment scenarios impossible with larger models: on-device inference, real-time applications, and privacy-preserving local processing.
Also known as
SLM, small LLM, compact language model, edge language model