Small Language Models
$0.99
Buy on Amazon View on Apple BooksPrefer it in print? See every format on Amazon →
Price on Apple Books. Amazon’s price may differ.
- Published
- Genres
- Computers & Internet
Description
Small Language Models is a practical, end-to-end guide to building AI with compact language models that run on phones, tablets, laptops, edge servers and modest data-center hardware. It explains what makes a model small, why small models matter for latency, cost, privacy, offline work, energy and sovereignty, and where they win and lose against large models. Readers learn how small models are made, how to quantize them with GGUF, GPTQ and AWQ and measure the quality loss, how to choose on-device runtimes, and how to build memory, latency and battery budgets from first principles. The book then shows how to evaluate small models on narrow tasks, fine-tune them with LoRA and QLoRA, distill large teachers into small students, produce reliable structured output and function calls, and build retrieval that runs entirely on the device. Later chapters cover hybrid routing and cascades with worked cost math, agents on small models, serving at scale on CPUs and small GPUs, and security, privacy and fleet operations. One running example, a field-service company with an offline assistant on rugged tablets and a back-office extraction pipeline, ties every chapter together.
This book is an independent publication and is not authorized, sponsored or endorsed by any company whose products it mentions. All trademarks belong to their respective owners and are used only for identification. This book was drafted with generative AI tools and checked with automated tools. Tools, features and prices change often; confirm them in current documentation.