Unified memory
Also: shared memory pool
One big pool of memory shared by a computer's processor and graphics, as on Apple Silicon Macs. Big models fit; they just run a bit slower than on a fast graphics card.
The fuller definition
Unified memory is a single pool of memory shared by the processor and the graphics on one chip, as in Apple Silicon Macs and some newer PCs. Most of the pool can hold a model, so large models fit without a separate graphics card.
- One pool
Processor and graphics share it
- Capacity
Large models fit
- Bandwidth
Usually below a fast graphics card
A simplified relationship, not a screenshot or a complete design.
A concrete example
A Mac Studio with 128 GB of unified memory can load a 63 GB model that no single consumer graphics card can hold.
The distinction that matters
Unified memory is large but usually slower than a graphics card's dedicated memory, so models fit more easily and write more slowly.
Related terms
VRAM — Video random-access memory
The memory on the graphics card. A model has to fit in it to run quickly.
Hardware & hostingRAM — Random-access memory
A computer's short-term working memory. Programs and data live here while in use.
Hardware & hostingMemory bandwidth
How fast data moves out of memory, in gigabytes per second. Think of it as the width of a loading door: wider means the model writes words faster.
Where it is taught
Understand the hardware a local model needsSource and further reading
Hugging Face · Model inference and quantizationThe definition and example are written for this library. The link gives background, official documentation or legal authority as labelled. Legal scope depends on the jurisdiction and current text; product features depend on release and settings.