Symbol Q^*_device
evice is part of the quantity the equation computes from the expression on the right.
Read this term in its guide →Published equation contexts
Why this formula appears here
The marginal-cost argument for on-device inference is not wrong; it is one term in a four-term equation, and the other three — variant-matrix engineering, distillation-versus-teacher economics, and update-distribution bandwidth — are each individually documented at real, checkable magnitudes in this article. Distillation itself is nearly always worth doing: disclosed training runs in the hundreds of dollars clear their own break-even point against even modest cloud query volumes almost immediately. Placing the result on a device is a separate, harder calculation, one that rises with every additional tier a release has to validate and every device already in the field that has to receive the…
Read the representative guide
Symbol C_dev
ev is one of the signed contributions combined to compute the quantity on the left.
Read this term in its guide →Symbol U
U is one of the signed contributions combined to compute the quantity on the left.
Read this term in its guide →Symbol c_cloud
loud is one of the signed contributions combined to compute the quantity on the left.
Read this term in its guide →Symbol c_d
is one of the signed contributions combined to compute the quantity on the left.
Read this term in its guide →How to interpret it
Read it with the definitions, units, and assumptions supplied by the article.
Published contexts (1)
A symbol can carry a different meaning in another article. Each occurrence keeps its own guide and term definitions.
Equation 37 · Edge AI & Electronics
The Real Economics of Shipping a Model to a Device
This equation states an equality: the expressions on both sides have the same value under the article’s assumptions.
The marginal-cost argument for on-device inference is not wrong; it is one term in a four-term equation, and the other three — variant-matrix engineering, distillation-versus-teacher economics, and update-distribution bandwidth — are each individually documented at real, checkable magnitudes in this article. Distillation itself is nearly always worth doing: disclosed training runs in the hundreds of dollars clear their own break-even point against even modest cloud query volumes almost immediately. Placing the result on a device is a separate, harder calculation, one that rises with every additional tier a release has to validate and every device already in the field that has to receive the…
Equation guide → · Article →