← All parts of this equation

Equation 9 · Part 1 · The Deployment Envelope: Small Models Where the Power Is Not

Symbol W

WW
WW

What this part means

the halving the bits per weight halves.

Its job in the formula

W is a part of this expression. Its role is fixed by the surrounding article and by the operations shown in the formula.

Where the article explains it

On a device it is primarily a bandwidth and energy intervention : halving the bits per weight halves W in the bound above and halves the bytes crossing the most energy-expensive interface in the system.

The passage around this formula

…reframes what quantisation is for. On a server, low precision is often discussed as a memory-capacity or cost measure. On a device it is primarily a bandwidth and energy intervention : halving the bits per weight halves W in the bound above and halves the bytes crossing the most energy-expensive interface in the system. Meta’s own report on quantised Llama 3.2 models claims “56% in model size”, a “41% average reduction in memory usage” and “2-4x speedup”, with “decode latency improved by 2.5x and prefill latency…

Read this part in the article →

Learn the underlying idea

A variable is a named place for a value. Its letter is a local label: x can mean position in one formula and a data point in another.

Open the illustrated variables: a letter stands for a value guide →

See this notation across published equations →

Sources cited in the surrounding passage

These citations provide research context; check each source for the exact claim it supports.