NodeValid

Published video-model weights, licences and hardware notes

What the repositories say you need to run them

Two hardware statements appear in the Wan repository and they do not agree with each other: one command is described as running on a consumer 4090, others are given a floor of 80GB of VRAM. The LTX-Video repository states no minimum and ships smaller variants instead. As of 2026-09-12.

Which releases state a hardware figure at allFilled where the repository states a requirement in that column, hollow where it states none. Some name a card, some name a number -- the wording is quoted in the rows below and never derived from parameter counts. Recorded 2026-09-12.Which releases state a hardware figure at allStated requirementAs writtenWan 2.2 TI2V-5BWan 2.2 TI2V-5B — Stated requirement: Consumer card named: a 4090Wan 2.2 TI2V-5B — As written: 5-second 720P clip in under 9 minutes on a single consumer GPUWan 2.2, other commandsWan 2.2, other commands — Stated requirement: At least 80GB of VRAMWan 2.2, other commands — As written: Stated in the same repositoryLTX-Video 13BLTX-Video 13B — Stated requirement: No minimum statedLTX-Video 13B — As written: Distilled and fp8 variants published for lower VRAM
Filled where the repository states a requirement in that column, hollow where it states none. Some name a card, some name a number -- the wording is quoted in the rows below and never derived from parameter counts. Recorded 2026-09-12.
Hardware requirements as the repositories state them. Recorded 2026-09-12.
ReleaseStated requirementAs written
Wan 2.2 TI2V-5BConsumer card named: a 40905-second 720P clip in under 9 minutes on a single consumer GPU
Wan 2.2, other commandsAt least 80GB of VRAMStated in the same repository
LTX-Video 13BNo minimum statedDistilled and fp8 variants published for lower VRAM

Inclusion rule. Statements taken from the model repositories themselves. A repository that gives no figure is recorded as giving none rather than having one estimated from the parameter count. Order. Grouped by repository, the specific statement before the general one.

1Two numbers in one repository, and both are true

The gap between a 4090 and 80GB of VRAM is the difference between a desktop and a rented server, so a reader who takes away one number has taken away the wrong one half the time. They describe different commands: the small text-to-video and image-to-video release is the one paired with the consumer card, and the heavier commands in the same repository carry the larger floor.

This register records both rather than resolving them, because resolving them would mean deciding which command a reader intends to run. What the two figures together do establish is that open weights do not have a single hardware answer, and that a claim of consumer-grade hardware attaches to a specific release rather than to a family.

2Nine minutes is a throughput figure, not a speed test

Under nine minutes for a five-second 720P clip is the only timing statement in either repository. Read as a ratio it is roughly a hundred seconds of compute for one second of output, which is the number that matters when the comparison is against a per-second price rather than against another card.

It is the vendor's own figure on the vendor's own chosen command, so it is the friendly case rather than an average. This site does not run the command, and a reader planning capacity should treat the figure as the shape of the answer rather than as their answer.

3Publishing smaller variants instead of a floor

The other repository takes the opposite approach: no stated minimum, and distilled and fp8 builds published specifically to run in less memory and finish faster. That is a statement about intent rather than a specification, and it leaves the reader to find their own floor by trying.

Neither approach is better and they fail differently. A stated figure can be wrong for your command; an unstated one cannot be wrong, and cannot be planned against either.

4What the hosted rate buys instead

The alternative to hardware is a published per-second rate, and two are recorded in this register: Wan 3.0 seconds sold from about $0.06 at 480P, and LTX-2.5 seconds from $0.09. Against roughly a hundred seconds of compute per second of output, the comparison a team is actually making is a rate against a card plus the hours to keep it busy.

The versions on each side are not the same, which is the finding this whole register keeps returning to: the weights that exist are an earlier generation than the seconds that are sold. A cost comparison that ignores that is comparing a price with a different product.

5Sources

Hardware statements are from the Wan2.2 and LTX-Video repositories, read 2026-09-12. The hosted rates are from ltx.io and scenemixer.com, and both are recorded with their versions on the hosted pages. What counts as a published statement is on how read.

  • Hardware
    The repository states TI2V-5B runs on consumer-grade graphics cards such as a 4090, generating a 5-second 720P video in under 9 minutes on a single consumer GPUvendor's own figureWan-Video, Wan2.2 repository / recorded 2026-09-12
  • Hardware
    Other commands in the same repository state a requirement of at least 80GB of VRAMthe larger modelsWan-Video, Wan2.2 repository / recorded 2026-09-12
  • Published models
    A 13B model, with distilled and fp8 variants published for lower VRAM and faster inferenceseveral variantsLightricks, LTX-Video repository / recorded 2026-09-12
  • What the hosted service sells
    Wan 3.0 seconds at published per-second rates, from about $0.06 at 480PSceneMixer, price list / recorded 2026-09-12
  • What the hosted service sells
    LTX-2.5 API seconds at $0.09 to $0.39LTX Studio, API / recorded 2026-09-12