README: iPhone 18 Pro load numbers of the JIT bundles in ios/

README.md

@@ -102,10 +102,19 @@ clip (a hand pushing a block); point `--video` at real footage for real results.
 | `macos/labels.json`, `ios/labels.json`, `ios-h18p/labels.json` | 174 SSv2 class names |
 | `macos/metadata.json`, `ios/metadata.json` | I/O + preprocessing spec |
 
-The JIT bundle in `ios/` has not been run on an iPhone yet. The iPhone 18 Pro specialized other JIT
-graphs of up to 1.6 GB on its own. It refuses an h18p bundle with
-`incompatibleCompiledAssetArchitecture`
+Measured 2026-09-26 on an iPhone 18 Pro (iPhone19,2, iOS 27.0 build 24A437, h19p) with the zoo's
+DecideGate app in its load-only mode, without the increased-memory entitlement. Each first load was the
+graph's first in an app container that held no specialization of it; the app had run other graphs
+before. The call is one run on all-zero inputs. Each first load wrote a specialization of about the
+bundle's size into the app container, and the load after a relaunch reused it. One measurement per graph
 ([knowledge/jit-distribution.md](https://github.com/john-rocky/coreai-model-zoo/blob/main/knowledge/jit-distribution.md)).
+The same phone refuses an h18p bundle with `incompatibleCompiledAssetArchitecture`.
+
+| JIT bundle in `ios/` | MB | first load | first call | load after relaunch |
+|---|---:|---:|---:|---:|
+| `vjepa2_ssv2_fp16.aimodel` | 708 | 2.22 s | 1,195 ms | 0.56 s |
+
+The app's footprint peaked at 244 MB during the first call.
 
 **Live demo app**: [coreai-video](https://github.com/john-rocky/coreai-model-zoo/tree/main/apps/coreai-video)
 — camera → live top-3 actions. iPhone 17 Pro with the h18p AOT bundle: ~0.34 s per 16-frame clip.