NodeValid

Published video-model weights, licences and hardware notes

Which repositories state a minimum rather than a peak

Four of the 15 families publish a stated minimum. Two more publish a requirement figure, four publish a peak measurement, one publishes the memory a run used, one publishes only a timing, and three publish nothing. As of 2026-09-12.

Two kinds of memory figure, measured from opposite endsA peak reports the most a run held on whatever card the vendor used; a minimum reports the least a card must have to finish a described job.A peakA minimumReportsThe most a run held at onceThe least a card must haveCheap to produceOne line of instrumentationTesting hardware you may not ownTransfers downwardBadlyBy constructionInvites correctionNoYes, from anyone with that cardMeasured downward, or upward
Fig. 1 The left column is what most repositories publish and the right is what readers want.
How the hardware column is filled across the register, by the kind of statement made. Recorded 2026-09-12.
ItemWhat is publishedDetail
A stated minimumFour familiesFrom 4GB in FP16; 6GB for 1800 frames; at least 12GB on an fp8 build; at least 80GB
A requirement figureTwo families32.54 GB of VRAM; approximately 60GB on one GPU
A peak measurementFour families78.55 GB, 60.3GB, 60GB and around 51.2GB, each at a stated configuration
Memory a run usedOne family9.3G with offload and 27.5G without, on the same run
A timing and no memoryOne familyAbout 180s on an A100 80GB card
Nothing statedThree familiesNo figure, and in two cases no card either

Inclusion rule. One row per kind of memory statement. A kind used by a single family keeps its row, because the shape of the statement is the finding rather than the count. Order. From the statement most useful to a reader with one card to the least.

1Publishing a minimum is the harder choice

A peak falls out of instrumentation: run a script, report the maximum allocated. Establishing the smallest card that completes a job means acquiring or borrowing hardware the vendor may not have, and then standing behind the result.

That is why peaks outnumber minimums here, and why a minimum is usually conservative. A vendor that publishes one has accepted that anybody with that card will test it.

2The two kinds do not convert into each other

A run that peaked at 60GB on an 80GB card may still need a different offload strategy to fit on anything smaller, and a 6GB minimum says nothing about how much headroom a large card would have. Reading one as the other is the commonest error in this column.

The register keeps the vendor's own word in the value. Where a repository says peak, the cell says peak, and where it says minimum or requires, the cell says that instead.

3The three silent releases are not all silent in the same way

One discusses offloading without ever giving a figure, which at least tells a reader that memory was a consideration. One names no card and no number at all. One publishes smaller builds instead of a figure, which is an answer in a form this column cannot hold.

All three are recorded as absences. A number from a forum thread would be the only value on those rows that nobody published, and it would be the one readers quoted.

  • Hardware
    To generate a 1-minute video at 30fps, 1800 frames, using the 13B model, the minimal required GPU memory is 6GBa floor stated together with the output it buyslllyasviel, FramePack repository / recorded 2026-09-22
  • Hardware
    From 4GB in FP16 for the 2B model, from 5GB in BF16 for the 5B, and from 10GB for CogVideoX1.5-5Bthe lowest figures the repository statesTHUDM, CogVideo repository / recorded 2026-09-12
  • Hardware
    For 4.5B models, any machine with at least 24GB of GPU memory is sufficient, and a distilled fp8 configuration works on GPUs with at least 12GBa floor for the model and a lower one for a buildSandAI-org, MAGI-1 repository / recorded 2026-09-22
  • Hardware
    78.55 GB peak GPU memory at 768px768px204f, 77.64 GB at 544px992px204f and 72.48 GB at 544px992px136fstated per configuration at batch size onestepfun-ai, Step-Video-T2V repository / recorded 2026-09-22
  • Hardware
    SVD-XT takes about 180s on an A100 80GB carda timing on a named card with no memory floor statedstabilityai/stable-video-diffusion-img2vid-xt on Hugging Face / recorded 2026-09-22

4Sources

Repository statements and hosted rates are linked from the model pages and the how read page, checked 2026-09-12. Hardware figures are set out on requirements. Nearby: Figures, no card, Frames, no rate, Exact or rounded.