# Batch Size

> How many examples the model reads before each update. Often 32 or 64.

**Field:** Artificial Intelligence  
**Category:** Machine Learning  
**Also known as:** Mini-Batch Size, Batch (Machine Learning)

## Think of it like

Think of it like marking tests in piles. You check one pile, fix your notes, then take the next pile.

## Definition

Batch size is how many examples a model looks at before it updates its weights. Training does not use all the data at once. It splits the data into small groups called batches, often 32 or 64 examples each. After each batch, the weights take one step. Bigger batches use more memory, and smaller ones give noisier steps.

## Example

Lucy has 1,000 examples and a batch size of 100. Each epoch has 10 batches, so the weights get 10 updates per pass.

## Why it matters

It changes how fast training runs and how much memory it needs. A batch too big for the chip will not run at all.

## Common mistake

Raising the batch size without changing the learning rate. The two work together, so changing one often means changing the other.

## Three principles

- **Examples per step.** How many before one update.
- **Splits the data.** Into many small batches.
- **A trade.** Bigger needs more memory.

## Related terms

- [Epoch](https://learn.benibix.com/term/ai/epoch)
- [Gradient Descent](https://learn.benibix.com/term/ai/gradient-descent)
- [Learning Rate](https://learn.benibix.com/term/ai/learning-rate)
- [Hyperparameter](https://learn.benibix.com/term/ai/hyperparameter)

## Told apart from

- [Epoch vs Batch Size](https://learn.benibix.com/compare/epoch-vs-batch-size): People often think an epoch is one training step. It is a full pass over all the data. Batch size is how many examples go into one step. So with 1,000 examples and a batch size of 100, one epoch takes 10 steps.

## Taught in

- [Gradient Descent and Backprop](https://learn.benibix.com/learn/ai-machine-learning/gradient-descent-and-backprop): Machine Learning, 14/18

![A bar of 1,000 examples cut into 10 batches of 100. Each batch leads to one weight update. All 10 batches together make one epoch.](https://learn.benibix.com/diagrams/nn-epoch-batch.svg)

---

Source: https://learn.benibix.com/term/ai/batch-size
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: 2026-11-17
Licence: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Quote freely with attribution.
