# Video Memory (VRAM)

> The GPU's own fast memory. A model must fit in it to run on the GPU.

**Field:** Infrastructure  
**Category:** Hardware  
**Also known as:** VRAM, GPU Memory, Graphics Memory

## Think of it like

Think of it like the GPU has its own desk. It is right next to it, so it does not walk far.

## Definition

Video memory is the fast memory on a graphics card that only the GPU uses. It sits right next to the GPU chip. For the GPU, it is much faster than normal RAM. To run an AI model on a GPU, the model's weights usually have to fit in its video memory. Home graphics cards often have 8 to 32 gigabytes, and data centre GPUs have 80 or more.

## Example

Emma's graphics card has 12 GB of video memory. A model with 7 billion weights at 2 bytes each needs about 14 GB, so it does not fit.

## Why it matters

To run AI at home, video memory is most often the limit. It decides the biggest model you can load.

## Common mistake

Counting only the weights. Running a model also needs room for the text it is working on, which can take several more gigabytes.

## Three principles

- **On the graphics card.** Right beside the GPU.
- **Very fast.** Quicker for the GPU than RAM.
- **The model must fit.** Or it will not run there.

## Related terms

- [Graphics Processing Unit (GPU)](https://learn.benibix.com/term/infrastructure/graphics-processing-unit)
- [Random Access Memory (RAM)](https://learn.benibix.com/term/infrastructure/random-access-memory)
- [Memory Bandwidth](https://learn.benibix.com/term/infrastructure/memory-bandwidth)
- [Model Parameter](https://learn.benibix.com/term/ai/model-parameter)
- [Parameter Count](https://learn.benibix.com/term/ai/parameter-count)
- [Quantization (AI)](https://learn.benibix.com/term/ai/quantization)
- [Model Memory Requirements](https://learn.benibix.com/term/ai/model-memory-requirements)

## Told apart from

- [RAM vs VRAM](https://learn.benibix.com/compare/ram-vs-vram): People often think a computer's memory is one pool that every chip shares. With a graphics card, there are two. RAM belongs to the CPU, and video memory sits on the card for the GPU alone. A model that fits in 32 GB of RAM can still be too big for a GPU with 12 GB of video memory.
- [Unified Memory vs Video Memory (VRAM)](https://learn.benibix.com/compare/unified-memory-vs-vram): People think unified memory is just video memory with a new name, and it is not. Video memory sits on a graphics card for the GPU alone. Unified memory is one pool that the CPU and GPU share. So a 64 GB pool is not 64 GB for the GPU, since the system and apps use it too.

## Taught in

- [VRAM and Unified Memory](https://learn.benibix.com/learn/infrastructure-hardware/vram-and-unified-memory): Computer Hardware, 5/8

![A CPU joined to RAM by a thin pipe, and a GPU joined to its video memory by a thick pipe. The pipe width is the memory bandwidth.](https://learn.benibix.com/diagrams/hw-memory.svg)

---

Source: https://learn.benibix.com/term/infrastructure/video-memory
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.
