# Model Pruning

> A way to shrink a model. The parts it needs least are cut out.

**Field:** Artificial Intelligence  
**Category:** Running Locally  
**Also known as:** Pruning (AI), Neural Network Pruning, Weight Pruning

## Think of it like

Think of it like trimming a bush. You cut the weak twigs, and it still looks like the same bush.

## Definition

Model pruning makes a model smaller by taking out the parts that matter least. It can take out single weights that are close to zero. Or it can take out whole parts, such as neurons, attention heads or layers. After pruning, the model is often trained a bit more, so it can make up for what was lost. Taking out whole parts is what makes it run faster on normal hardware. Pruning is often used with quantization and distillation.

## Example

A team prunes a quarter of the layers from a speech model and trains it for one more day. It runs a third faster on phones and scores almost the same.

## Why it matters

It shrinks a model in a new way, not like quantization. So the two can be used at once.

## Common mistake

Cutting single weights and hoping it runs faster. Zeros spread all over save space but often no time, unless whole parts are cut.

## Three principles

- **Cut what matters least.** Weights or whole parts.
- **Train a little more.** To recover.
- **Whole parts for speed.** Scattered cuts save space.

## Related terms

- [Quantization (AI)](https://learn.benibix.com/term/ai/quantization)
- [Knowledge Distillation](https://learn.benibix.com/term/ai/knowledge-distillation)
- [Weight (Neural Network)](https://learn.benibix.com/term/ai/weight)
- [Small Language Model (SLM)](https://learn.benibix.com/term/ai/small-language-model)

## Told apart from

- [Quantization vs Model Pruning](https://learn.benibix.com/compare/quantization-vs-model-pruning): People often think quantization and pruning are the same way to shrink a model. Quantization keeps every weight but saves each one with fewer bits, like rounding. Pruning takes out the weights or parts that matter least, so there are fewer of them. The two work in their own ways, so they are often used together.

![A small network before and after pruning. The weakest links are cut away, and the network that is left is smaller and faster.](https://learn.benibix.com/diagrams/lo-model-pruning.svg)

---

Source: https://learn.benibix.com/term/ai/model-pruning
Author: Behnia Zarei (a developer in Vienna, Austria, who builds and teaches data, AI and business intelligence at BENIBIX)
Publisher: BENIBIX Learn (https://learn.benibix.com/)
Last updated: 2026-11-19
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
