The site keeps these states separate so results and claims remain interpretable.
Support center
The user guide for how VRAM Check scores, ranks, and explains local AI hardware.
Use this page when you want the rules in plain language: how the benchmark works, what makes a run official, how classes are assigned, and what the most common support questions actually mean.
Real inference, strict passes, runtime validation, and release verification are part of the public trust story.
How it works
A benchmark report, not just a score dump.
VRAM Check is designed to tell you what happened, why it matters, and what to do next.
The CLI reads the machine first so the benchmark stays anchored to the hardware you actually own.
The benchmark runs one fixed public profile with strict pass selection so verified runs stay comparable.
Each run is labeled as verified, provisional, compatibility, or estimated so the site never blurs one state into another.
The results page turns throughput, timing, stability, and bottleneck analysis into a readable report.
Methodology
What the canonical benchmark is actually measuring.
Leaderboard ordering starts with decode throughput. Prefill throughput and TTFT are tie-breakers and supporting evidence.
VRAM Check runs multiple canonical passes, selects a representative pass, and measures variance so noisy runs do not contaminate rankings.
Official releases publish a checksum and can be verified locally with vramcheck verify-release --file .\vramcheck-windows.exe.
Ranking rules
Leaderboard positions only count when the run earns them.
Runtime acceleration must be active and the execution profile must be verified GPU, not compatibility mode.
Decode, prefill, and TTFT variance must stay within the active policy to make rankings meaningful.
Compatibility and provisional runs still produce valuable result pages, but they do not claim official competitive rank.
Class system
Class tells you capability. Rank tells you competition.
VRAM Check keeps absolute capability separate from competitive position so the report stays easier to read.
Class is the absolute capability band of the machine under the active public benchmark.
Current public scale: S, A,B, C, D,E.
Rank is competitive context inside the active leaderboard scope.
A machine can have a modest class and still place well in a narrow field, or a strong class and a weaker rank in a crowded frontier board.
Key capabilities
Where the product is strongest today.
Runs one shared benchmark profile with real inference, runtime detection, release verification, and a strict stability policy.
Shows what your current build can run comfortably, what starts getting tight, and where an upgrade would materially change the result.
Separates verified leaderboard runs from compatibility and estimated states so competitive claims remain honest and defensible.