Fast memory a GPU uses to hold models and work data.
VRAM is the GPU’s desk. Big desk: the laptop and snacks fit. Tiny desk: one elbow starts a disaster.
It decides if a model runs smoothly on your computer. It also matters during training and when a model answers.
GPU
VRAM is the GPU’s closest memory, so many GPU limits are VRAM limits.
Quantization
Quantization shrinks a model, so it needs less VRAM.
Local-LLM
When you run a Local-LLM, VRAM often decides how big it can be.
Parameter
More parameters usually use more VRAM during loading and work.