Leanpub Header

Skip to main content

Winning Big With Small AI

  1. Timely Relevance: Edge AI is currently undergoing rapid adoption and transformation
  2. Practical Focus: Each topic includes concrete business opportunities and implementation strategies
  3. Broad Appeal: Covers both technical and business perspectives
  4. Forward-Looking: Includes emerging trends that will remain relevant for years
  5. Case Study Rich: Plenty of real-world examples from startups and established companies

Minimum price

$8.00

$12.00

You pay

$12.00

Author earns

$9.60
$

...Or Buy With Credits!

You can get credits with a paid monthly or annual Reader Membership, or you can buy them here.
PDF
EPUB
WEB
About

About

About the Book

Using AI models does not always mean using Super Scalers like Google and OpenAI. This book covers use cases where using smaller models that meet system requirements can save money and be run locally for privacy and security.

Share this book

Author

About the Author

Mark Watson

Author Mark Watson has been using neural network technology since 1984 for commercial applications (both software and custom hardware). Here Mark argues that “big is not always better” when using LLMs and urges his readers to choose appropriate technology for specific use cases.

Leanpub Podcast

Episode 253

An Interview with Mark Watson

Contents

Table of Contents

Preface

  1. Choosing Which “Small AI” Tools to Use in This Book

Part I - Advantages of Small AI With Examples

Advantages of Small Models with Examples That Might Surprise You

  1. The Great Divergence: Redefining Intelligence in the Post-Scale Era
  2. The Cloud Efficiency Champion: Anatomy of Gemini 3 Flash
  3. The Local Insurgency: Qwen 3 and other Local Models Provide Democratization of Reasoning
  4. The Physics of Thought: Theoretical Mechanisms
  5. Sovereignty and Solvency: The Economic and Legal Case
  6. Surprising Realities: Case Studies
  7. Horizon 2026: The Future of Distributed Intelligence

Drawbacks of Small AI

  1. Reduced Reasoning Depth and Nuance
  2. Higher Propensity for Hallucination
  3. Limited Context Window and Memory Management
  4. Fragility in Prompt Following
  5. Security and Support Disparities
  6. Wrap Up for Drawbacks of Small AI

Part II - Defining Metrics for Success Using LLMs

Defining Metrics for Success Using LLMs

  1. Operational Metrics: The Small AI Advantage
  2. Quality Metrics: The “LLM-as-a-Judge” Pattern
  3. RAG Metrics: The Trinity of Trust
  4. Deterministic Guardrails
  5. The Golden Ratio: Accuracy per Watt
  6. Code Example: The Judge Pattern
  7. Wrap Up for LLM Metrics

A Fair Shootout: Evaluating Large vs. Small Models for Task Fitness

  1. The Setup for RAG: David vs. Goliath
  2. Fairness: Adjusting Problem Setups for Small vs. Large Models
  3. Comparing Small vs. Large Models for NLP and Extracting Structured Data From Text
  4. Wrap Up for Evaluating Large vs. Small Models for Task Fitness

Part III - Python Examples for Switching Between Models

Using the LiteLLM Library to Easily Switch Between Models and Model Providers

  1. Tool Use with LiteLLM
  2. LiteLLM Wrap Up

Automatically Routing to the ‘Best’ Model Using RouteLLM Library

  1. Implementation of a Command Line Query Utility Using RouteLLM

Wrap Up for Winning Big With Small AI

  1. The Engineering Reality: From Vibes to Metrics
  2. The Architecture of Hybrid Intelligence
  3. The “Fitness for Purpose” Philosophy
  4. Sovereignty, Solvency, and Sustainability
  5. Final Recommendations for Your Journey

The Leanpub 60 Day 100% Happiness Guarantee

Within 60 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.

Now, this is technically risky for us, since you'll have the book or course files either way. But we're so confident in our products and services, and in our authors and readers, that we're happy to offer a full money back guarantee for everything we sell.

You can only find out how good something is by trying it, and because of our 100% money back guarantee there's literally no risk to do so!

So, there's no reason not to click the Add to Cart button, is there?

See full terms...

Earn $8 on a $10 Purchase, and $16 on a $20 Purchase

We pay 80% royalties on purchases of $7.99 or more, and 80% royalties minus a 50 cent flat fee on purchases between $0.99 and $7.98. You earn $8 on a $10 sale, and $16 on a $20 sale. So, if we sell 5000 non-refunded copies of your book for $20, you'll earn $80,000.

(Yes, some authors have already earned much more than that on Leanpub.)

In fact, authors have earned over $14 million writing, publishing and selling on Leanpub.

Learn more about writing on Leanpub

Free Updates. DRM Free.

If you buy a Leanpub book, you get free updates for as long as the author updates the book! Many authors use Leanpub to publish their books in-progress, while they are writing them. All readers get free updates, regardless of when they bought the book or how much they paid (including free).

Most Leanpub books are available in PDF (for computers) and EPUB (for phones, tablets and Kindle). The formats that a book includes are shown at the top right corner of this page.

Finally, Leanpub books don't have any DRM copy-protection nonsense, so you can easily read them on any supported device.

Learn more about Leanpub's ebook formats and where to read them

Write and Publish on Leanpub

You can use Leanpub to easily write, publish and sell in-progress and completed ebooks and online courses!

Leanpub is a powerful platform for serious authors, combining a simple, elegant writing and publishing workflow with a store focused on selling in-progress ebooks.

Leanpub is a magical typewriter for authors: just write in plain text, and to publish your ebook, just click a button. (Or, if you are producing your ebook your own way, you can even upload your own PDF and/or EPUB files and then publish with one click!) It really is that easy.

Learn more about writing on Leanpub