Skip to the document
Madhuopen lab
Outcome School · Training and alignment19 min read

by Amit Shekhar · 11 June 2026

How does Knowledge Distillation work?

How Knowledge Distillation works. We will also see why we need it, how a small model learns from a big model, and how this lets us run powerful AI on a phone, on an edge device, and at low cost.

3,629 words#ai#machine-learning4 recall cards

How does Knowledge Distillation work?
Read on Outcome School ↗then come back to lock it in
Before you read, guess

What characterizes the small model, known as the student, in terms of speed, cost, and independent intelligence?

Ten seconds, a guess, then read — a wrong guess still makes the answer stick.

What this article covers

  1. What is Knowledge Distillation?
  2. Why we need Knowledge Distillation
  3. Hard labels vs soft labels
  4. Dark knowledge
  5. Temperature in the softmax
  6. The distillation loss
  7. A step-by-step training walkthrough
  8. Types of Knowledge Distillation
  9. Real examples of Knowledge Distillation

The article lives on outcomeschool.com. Read it there, then come back: the tutor in the margin has read it and will answer questions, and the questions below check what stayed.

Before you go

In one sentence, what was this chapter about?

From memory, without scrolling up. Writing it is what makes it yours; the grade is only to show you what you had.

How sure?