PromptForge
AI Glossary

Models & architecture

Distillation

Also known as: knowledge distillation, distilled model

Definition

Distillation trains a smaller model to imitate a larger one, transferring much of the capability at a fraction of the inference cost. Most small production models are distilled from bigger teachers.

The student model trains on outputs from the teacher rather than only on raw text. Because the teacher provides richer signal than a single correct label — including its uncertainty across options — the student learns more efficiently than it would from the original data alone.

Distillation is why the small-model tier has improved so quickly. A distilled 8B model can approach the quality of a much larger model on the specific distribution of tasks it was distilled for, while costing a small fraction to run.

The limitation is generality: distilled models tend to match their teacher on covered task types and fall off more sharply outside them.

Related terms

Put this into practice

Understanding the term is step one. Our free courses and tools let you actually use it.