Skip to content
BENIBIX Learn

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.

Infrastructure🔧 Hardware

Random Access Memory (RAM)

Fast memory for the work being done right now. It empties when power goes off.

Random access memory is the fast, short-term memory a computer works from. Programs and their data are loaded into RAM from storage so the CPU can reach them quickly. It is much faster than a disk, but it is emptied when the power goes off. A laptop often has 8 to 32 gigabytes. To run an AI model on the CPU, the whole model usually has to fit in RAM.

Example
Jack's laptop has 16 GB of RAM. A model file of 20 GB will not fit, so it will not load on the CPU.
Why it matters
RAM size limits what can run at once. For AI on your own machine, it often decides which models you can use.
Full entry
Infrastructure🔧 Hardware

Video Memory (VRAM)

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

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.
Full entry

In one line

Random Access Memory (RAM)
Fast memory for the work being done right now. It empties when power goes off.
Video Memory (VRAM)
The GPU's own fast memory. A model must fit in it to run on the GPU.