Card: state where each on-device figure actually comes from; replace the iPhone row with a fresh measurement where one was taken

README.md

@@ -114,7 +114,7 @@ reduction is required to fit iOS.
 
 Reproducibility: the GPU rows repeat to within about 1% across invocations; the CPU rows are noisier — re-running the 1B control six times spread its CPU decode over 29.0–33.3 tok/s, so treat the CPU column as accurate to roughly ±7%.
 
-The desktop rows are the shipped `model.litertlm` (block 32); the block-128 build was not re-measured, so the figures for it in “Which file?” above are the older ship-gate numbers. The iPhone figures are single cold runs from that gate, one per build.
+The desktop rows are the shipped `model.litertlm` (block 32); the block-128 build was not re-measured, so the figures for it in “Which file?” above are the older ship-gate numbers. The iPhone figures come from the 2026-06-27 on-device platform matrix for this model, one per build; that record does not state a run count or prompt.
 
 ### Accuracy note