Small Language Models & On-Device AI
Learn why small, efficient language models running on-device or at the edge are a distinct design choice from large hosted models — and when that trade-off makes sense.
Small, efficient models running on-device are a distinct architectural choice, not a lesser version of a large model. These lessons cover when the trade-off makes sense, how to choose between a small local model and a large hosted one, and what shipping a model to a real phone or embedded device actually requires.
What Are Small Language Models, and Why They Matter
Understand the distinct role small, efficient models play alongside large frontier models rather than as a lesser substitute.
7 min read →Choosing Between a Small Model and a Large Hosted Model
Learn a practical framework for deciding when a small on-device model is the right architectural choice versus a large API-based model.
7 min read →Deploying Small Models to Edge and Mobile Devices
Learn the practical steps and constraints involved in shipping a language model that runs directly on a phone, browser, or embedded device.
7 min read →