Which AI models can my PC run?
The answer comes down mostly to your graphics card's VRAM. Pick your card below to see which of 228 local AI models fit, or scan your PC for an exact answer that also accounts for your RAM, disk space and installed acceleration backends.
NVIDIA graphics cards
AMD graphics cards
Browse by VRAM instead
Know how much memory your card has but not its exact model? Start here.
How much VRAM do you need to run AI models locally?
As a rough guide: 8GB comfortably runs models up to about 8B parameters at 4-bit quantization, which covers most general chat and coding assistants. 12–16GB opens up 13B–14B models and longer context windows. 24GB and above handles 30B-class models entirely on the GPU.
VRAM is not the only constraint. A model that does not fit can still run by offloading part of itself to system RAM, which works but is much slower. The PC scan measures all of it — VRAM, RAM, disk and whether CUDA, ROCm or Vulkan is actually available on your machine.