diff --git a/.github/workflows/apple-perf.yml b/.github/workflows/apple-perf.yml
index 4fb3e9711db..50208268757 100644
--- a/.github/workflows/apple-perf.yml
+++ b/.github/workflows/apple-perf.yml
@@ -341,7 +341,7 @@ jobs:
       - set-parameters
     secrets: inherit
     with:
-      runner: macos-latest-xlarge
+      runner: macos-15-xlarge
       python-version: '3.11'
       submodules: 'true'
       ref: ${{ github.event_name == 'pull_request' && github.event.pull_request.head.sha || github.sha }}
@@ -351,6 +351,9 @@ jobs:
       script: |
         set -eux
 
+        echo "Setting XCode version"
+        sudo xcode-select -switch /Applications/Xcode_16.2.app
+
         echo "::group::Setting up CI environment"
         .ci/scripts/setup-conda.sh
 
diff --git a/extension/benchmark/apple/Benchmark/README.md b/extension/benchmark/apple/Benchmark/README.md
index 79daf070e44..cea2d1c7442 100644
--- a/extension/benchmark/apple/Benchmark/README.md
+++ b/extension/benchmark/apple/Benchmark/README.md
@@ -72,6 +72,15 @@ kernels_portable.xcframework
 kernels_quantized.xcframework
 ```
 
+#### MLState
+The prebuilt frameworks do not work with CoreML models that use MLState, which is used in LLM models exported for iOS18.  When executing the *.pte file, you will see an error like:
+
+```
+The input feature for X must be an MLState, but it was not.
+```
+
+If you encounter this issue, build the frameworks locally (option 2) using **XCode 16.0** or higher.
+
 ## Adding Models and Resources
 
 Place your exported model files (`.pte`) and any other resources (e.g., `tokenizer.bin`) into the `extension/benchmark/apple/Benchmark/Resources` directory:
diff --git a/extension/llm/export/partitioner_lib.py b/extension/llm/export/partitioner_lib.py
index 74a521a61b5..19c89596765 100644
--- a/extension/llm/export/partitioner_lib.py
+++ b/extension/llm/export/partitioner_lib.py
@@ -158,11 +158,7 @@ def _validate_ios_version() -> None:
         op_linear_quantizer_config=op_linear_quantizer_config,
     )
 
-    # ExecuTorch does not build CoreML delegate runtime to handle state
-    # when using OSS scripts, so we define take_over_mutable_buffer = False,
-    # even when target is iOS18
-    # take_over_mutable_buffer = minimum_deployment_target >= ct.target.iOS18
-    take_over_mutable_buffer = False
+    take_over_mutable_buffer = minimum_deployment_target >= ct.target.iOS18
     return CoreMLPartitioner(  # pyre-fixme[16]
         compile_specs=compile_specs,
         take_over_mutable_buffer=take_over_mutable_buffer,