NodeValid

Published video-model weights, licences and hardware notes

Why a pair of figures beats a single number

A single published figure describes one point. Two figures with one variable between them describe a direction, which is what a reader planning a different configuration actually needs, and it is the rarer form of publication. As of 2026-09-12.

A point against a gradientOne figure fixes a configuration; two figures with a single variable between them let a reader move away from it with some confidence.One figureTwo, one variable apartWhat it describesA configurationA directionAdjustableNoWithin the range measuredCost to publishOne runTwo runsRisk of misreadingRead as a general limitRead as a rule beyond its rangeOne variable, or no gradient
Fig. 1 The right-hand column is what makes a figure reusable outside its own settings.
Variables worth isolating between two published figures. Recorded 2026-09-12.
VariableWhat the pair reveals
Offload stateWhat memory the technique returns, and at what cost in time
Frame sizeHow much of the figure is activations rather than weights
Model sizeWhat the parameter count adds at a fixed output
Card countWhat sharding actually saves, which is not a division

Inclusion rule. Variables that can be isolated between two memory figures. Each row is a general measurement shape rather than a vendor value. Order. From the variable a reader controls at run time to the one that needs new hardware.

1The second figure costs one more run

A vendor that has instrumented one configuration can instrument a second for the price of another run. The reason pairs are rare is not cost; it is that publishing a second figure invites questions about the range between them.

That is precisely the range a reader needs. A pair turns a claim into a shape, and a shape can be extrapolated a short distance with some confidence.

2Only a controlled pair is a gradient

Two figures that differ in resolution and model size at once describe two runs. The difference between them cannot be attributed to either variable, and the ratio is a number with no meaning.

Checking what is held constant is therefore the first step with any pair. Where the output is held constant and the model varies, or the card is held constant and the frame varies, the pair is worth something.

3Pairs also bound the extrapolation

A gradient measured between two points says nothing reliable outside them. Doubling a resolution beyond the largest measured configuration is not covered by a ratio taken inside the range.

This is the failure mode a pair invites: a reader who has a direction will follow it further than the measurements support. The register records both points rather than a slope for that reason.

4The sharding pair is the one worth hunting for

Multi-card figures are the least intuitive in this field, because activations and buffers are replicated while only part of the load is split. A single-card figure beside a multi-card one is the only honest answer to what extra cards buy.

Anyone assuming linear scaling will under-budget substantially. It is the one place where the absence of a pair reliably costs money.

5Both sides of a trade belong in public

Where a technique lowers memory and raises runtime, publishing only the lower figure is accurate and misleading. A reader budgeting throughput would plan against a number that assumes the slow path.

Publishing only the higher figure is misleading in the other direction, and discourages users the release can serve. Two figures cost one extra line and remove both errors.

6What to do with a single figure

Treat it as a ceiling on confidence rather than as a specification. Plan at or below the configuration it was measured at, and test before scaling anything.

Where a release publishes one figure and a set of smaller builds instead of a second, the builds are the gradient in a form no column can hold. That is worth reading as an answer even though it is not a value.

7Where the repository figures are kept

The techniques above are general. Which vendors have published what, under which licence and on what hardware, is recorded on the model pages, each figure quoted from the repository it was read from with its date.

Craft notes on reading releases. No row here is attributed to a vendor, and nothing on this page is a reading of anyone's licence obligations. The sourced material is on the requirements page. Related: Limits of a register, Choosing a build.