HEADROOM_
local ai · measured · no account, no telemetry
webgpu · fp64-gated · receipts attached

How fast is your machine, really?

A 30-second test of your device's true memory-bandwidth ceiling for local AI: the number that decides your tokens/s. It also checks your driver for the subgroup bug that makes some in-browser LLMs produce garbage.

No model download, no account, no telemetry. Synthetic weights, FP64-checked. One outbound request: ~0.4 MB of public model metadata to derive bytes per token, no run data attached. Your numbers stay in this browser unless you post them.

CAN'T RUN: NO WEBGPU

band: the engine we measured redline: your 100%
~30 s
full suite
0 B
model download
FP64
reference gate before timing
med·5
medians, not bests
HEADROOM · RUN RECEIPTCANARY —
tok/s ceiling
gemma 4 e2b class · 2.46 GB resident
0kernel efficiency —ceiling —
gemma 4 e2b qat · 2.46 GB (per-layer embeddings, ~1.05 GB/token est)
8b class q4 · ≈4.7 GB dense
bonsai 27b 1-bit · ~3.8 GB (est; weights repo is gated)
SUBGROUP CANARY: —HEADROOM

Projections are measured read bandwidth ÷ bytes touched per token, at empty context; derived manifests make bytes-per-token exact, estimates fall back to an honest band. Real engines land below the ceiling; the gap is engine overhead (see methodology).

What your ceiling means

Reference points, measured by this page and receipted: an RTX 5070 reads 577-589 GB/s across three sessions (86-88% of its 672 spec) for a gemma 4 e2b ceiling of 717-731 tok/s, and the one in-browser engine we measured decodes 217 (30% of ceiling). An Apple M1 reads 51-56 GB/s for a ceiling of 63-69; the same engine does 30-40, while native Ollama on that M1 runs its model at 72-79% of ceiling. The gap is engine overhead, not bandwidth: that is the headroom. receipts · methodology

View the kernels: the exact WGSL this page times

Every timed kernel, verbatim, including the canary shapes. If you think a probe is unfair, the code to attack is right here.

Receipts: every number, its method
proberesultbytes/passiters × repsgate
RUN SHEET: every probe, livedetecting device…
preparing…