Everything on this page was measured by our own team, on our own hardware. That's why every number carries an internal benchmark label — there are zero third-party reproductions yet. When external runs land, they get their own badge. Until then, treat these as our claims, not the community's.
Two runs are public so far. Both were executed warm on an RTX 3090 (24 GB) under the Internal Verified environment class. No user data appears in this feed — capsule id, environment class, and timing only.
Timing is wall-clock for the render step on a warm engine (weights resident, first run excluded). Numbers are profile-conditional — resolution, frame count, step count, and model all change the result. This feed never includes prompts, file paths, account identifiers, or network addresses.
These measurements exist internally but did not pass our bar for publication yet. They are listed by name only — no numbers until re-verification completes.
Known limits (Public Preview): the full-INT8 residual projection path is disabled — it missed our accuracy bar, so only mixed INT8 is used. And to repeat the headline: there is no external reproduction data yet.
How the published numbers were taken:
The complete condition set — hardware state, driver/CUDA versions, repeat counts, and timing boundaries — will be documented in the benchmark-method document. Until it ships, this summary is the authoritative description.
The fastest way to turn "internal benchmark" into a verified number is an external run. Install free, run the same capsule, and file a compatibility report — successes and failures both count.