# Model Precision

> How many bits each weight in a model gets. Fewer bits make a smaller model.

**Field:** Artificial Intelligence  
**Category:** Running Locally  
**Also known as:** FP16, F16, BF16, Bfloat16, FP32, Half Precision, Floating-Point Precision

## Think of it like

It is like writing a price as 3.14159 or just 3.14. The short one takes less room.

## Definition

Model precision is how many bits each weight in a model gets. Full precision is 32 bits a weight, called FP32. Most open models are shared at 16 bits, as FP16 or BF16, which is half the size. BF16 holds the same range of big and small numbers as FP32, with less detail in each. Fewer bits mean a smaller file and faster running. Going below 16 bits is called quantization.

## Example

A model page lists the weights as BF16. Jack knows that means 2 bytes a weight. So a 7 billion weight model is about 14 GB.

## Why it matters

It sets the file size. It also sets the memory a model needs before any shrinking.

## Common mistake

Thinking FP16 and BF16 are the same. Both use 16 bits, but BF16 can hold far bigger and smaller numbers, with less detail in each.

## Three principles

- **Bits per weight.** Size grows with the bits.
- **16 is normal.** Half the size of FP32.
- **Below 16.** That step is called quantization.

## Related terms

- [Quantization (AI)](https://learn.benibix.com/term/ai/quantization)
- [Model Weights File](https://learn.benibix.com/term/ai/model-weights)
- [Model Memory Requirements](https://learn.benibix.com/term/ai/model-memory-requirements)
- [GGUF Quantization Type](https://learn.benibix.com/term/ai/gguf-quantization-type)
- [Floating-Point Number](https://learn.benibix.com/term/development/floating-point-number)
- [Byte](https://learn.benibix.com/term/development/byte)

![Bars for one 8 billion weight model saved at different precisions. At 32 bits it is about 32 GB. At 16 bits, as FP16 or BF16, about 16 GB. Q8_0 keeps about 8.5 bits a weight, about 8.5 GB. Q4_K_M keeps about 4.9 bits, about 5 GB, and is highlighted. A dashed line marks an 8 GB graphics card.](https://learn.benibix.com/diagrams/ai4-bits-per-weight.svg)

---

Source: https://learn.benibix.com/term/ai/model-precision
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.
