RTX 5090 Tested: Cutting H3 from 20 Steps to 4 — Where the Time Actually Goes

Updated 2026-09 · Data from local ComfyUI run logs and public benchmarks

This test machine: RTX 5090 32GB + 64GB DDR5-6000, running the official minimum setup (pruned INT8 main model 19.5GB + NVFP4 text encoder 14.6GB + two VAEs), launch flags --fast --use-sage-attention, and the LightX2V 8-step acceleration LoRA. Every number below comes from real logs, not estimates.

Start with the time budget

For the same 1344×768, 73-frame (~3-second) clip, here is the breakdown at 8 sampling steps:

StageTimeShare
Text encoder load + encode~11 s14%
Sampling (8 steps × 5.45 s/step)43.6 s54%
VAE decode + save~17.1 s21%
Other (scheduling, caching, etc.)~8.6 s11%
End-to-end80.3 s100%

Two takeaways: in short clips, sampling is only half the story — loading and decoding are another big chunk; the longer the clip, the higher the sampling share (token count grows with the attention quadratic term), and that is when acceleration really pays off in sampling.

Step compression: the real payoff of 20 → 8 → 4

Public benchmarks on the same machine, 1280×704, ~5-second clips (sampling segment only, excluding loading):

ConfigStepsSampling timevs. 20 steps
Official baseline20~270 s (extrapolated)1.0×
+ LightX2V Turbo 8-step8125 s2.2×
+ built-in INT8 attention (Kitchen)879 s3.4×
+ FastH3 4-step distillation4~60–70 s (inferred from 1.87×)~4×
One counterintuitive thing to note: per-step time is not constant. The 20-step profile costs about 13.5 s per step, but the 8-step profile actually rises to about 15.6 s — fewer steps does not reduce per-step overhead (LoRA patching and scheduler switching are still there), yet total time still drops substantially. So "steps ÷ 4 = time ÷ 4" only holds as a rough estimate.

How to stack the three acceleration layers correctly

  1. Step distillation (pick only one): LightX2V 8-step (smallest quality loss), 4-step (~3.4×), larryvrh Turbo 8-step, FastH3 4-step (~4×). Stacking two distillation LoRAs will break each other's effects;
  2. Attention backend (stackable, big gains): SageAttention or ComfyUI 0.32+'s built-in Kitchen attention, speeding up the sampling segment another 1.4–2×. On a 512-step run, this layer is essentially free;
  3. Caching (use with caution): EasyCache / Spectrum saves another 15–40%, but it works by skipping computation, so spot-check the frames; when batch-generating seeds from the same prompt, the lossless CLIPCached conditioning cache pays off more.

Quality trade-offs

How much time will your GPU need?

The numbers above only apply to the 5090. Sampling time on other GPUs depends mainly on memory bandwidth and architecture — open the WhichH3 calculator, pick your GPU, RAM, and page file settings, and it will estimate time and VRAM usage for every "resolution × duration × steps" combination, compare the 20-step / 8-step / 4-step acceleration options, and highlight the best setting for your machine.

Conclusion

Related pages: RTX 5090 32GB details · RTX 5090 D details · Acceleration compared