eng-0106
window recorded
citable URL: https://halobench.com/records/eng-0106/ — this address never moves; the anchor /records/#eng-0106 keeps resolving
4.54 Whmean 38.7 W − 10.1 W idle floor (box-idle-all-empty) = 28.6 W attributable
window 2026-08-15T18:20:30Z → 2026-08-15T18:27:33Z · provenance recorded
method wall-meter · aihydra energy sensor via Home Assistant (5-minute statistics on sensor.hardware_ai_hydra_energy, linearly interpolated to the run window) · no contention
covers run-0303
aihydra deepseek-v4-flash-fullbench throughput matrix cell. Wall-metered via HA sensor.hardware_ai_hydra_energy, joined from the permanent 5-minute statistics series (linearly interpolated to the exact run-meta window boundaries), not raw 10s history -- the matrix's ~4h span exceeded the history query's row cap by the time of ingest. Baseline 10.1 W is the repo's dated idle-aihydra-2026-08 box-idle-all-empty record. Window covers 1 rep(s) x 2 device-loss attempts each (2 crash+kernel-ring-reset cycles), not steady compute — this is NOT a throughput-comparable power figure.
Wh, never joules — read as a cumulative-counter difference across the window; delta over the idle baseline is the only figure that means anything