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.
| Release | Stated requirement | As written |
|---|---|---|
| Wan 2.2 TI2V-5B | Consumer card named: a 4090 | 5-second 720P clip in under 9 minutes on a single consumer GPU |
| Wan 2.2, other commands | At least 80GB of VRAM | Stated in the same repository |
| LTX-Video 13B | No minimum stated | Distilled 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.
- HardwareThe 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 figure
- HardwareOther commands in the same repository state a requirement of at least 80GB of VRAMthe larger models
- Published modelsA 13B model, with distilled and fp8 variants published for lower VRAM and faster inferenceseveral variants
- What the hosted service sellsWan 3.0 seconds at published per-second rates, from about $0.06 at 480P
- What the hosted service sellsLTX-2.5 API seconds at $0.09 to $0.39