gemma4_e2b_hostcache_chunk1_int8.aimodel: re-save with coreai-core 1.0.0b2 (strip debug locations; weights unchanged). The 0.4.0-era IR refused AIModel.load on every OS 27 build since beta 2, still on the RC 26A428 (2026-09-14); the re-saved bundle loads. Recovery: coreai-model-zoo conversion/recovery/{strip_b1,resave_b2}.py

ios-ane/gemma4_e2b_hostcache_chunk1_int8.aimodel/main.hash

@@ -1 +1 @@
-t��O�c�jf)g �Q�7U���A�ax�p
+�>ZD��U©�

ios-ane/gemma4_e2b_hostcache_chunk1_int8.aimodel/main.mlirb

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:749916c74ff263e9166a6629126720e9bc51e53755ef02f9b4411efc61788270
-size 299344372
+oid sha256:b43e5a44a1f055c2a9ee0d631ddab96af7292704b1e5fab0f5a5a9909433b761
+size 299276339

ios-ane/gemma4_e2b_hostcache_chunk1_int8.aimodel/metadata.json

@@ -1,3 +1,5 @@
 {
-  "assetVersion" : "2.0"
+  "producer" : "coreai-core 1.0.0b2",
+  "assetVersion" : "2.0",
+  "creationDate" : "20260914T112046Z"
 }