diff --git a/.ci/scripts/test_model.sh b/.ci/scripts/test_model.sh
index bc9bbb8bae0..c8e2f708878 100755
--- a/.ci/scripts/test_model.sh
+++ b/.ci/scripts/test_model.sh
@@ -91,11 +91,10 @@ test_model() {
     run_portable_executor_runner
     rm "./${MODEL_NAME}.pte"
   fi
-  STRICT="--strict"
+  STRICT="--no-strict"
   if [[ "${MODEL_NAME}" == "llava" ]]; then
     # Install requirements for llava
     bash examples/models/llava/install_requirements.sh
-    STRICT="--no-strict"
   fi
   if [[ "${MODEL_NAME}" == "qwen2_5" ]]; then
       # Install requirements for export_llama
diff --git a/examples/xnnpack/aot_compiler.py b/examples/xnnpack/aot_compiler.py
index f67150169dc..79496c82a58 100644
--- a/examples/xnnpack/aot_compiler.py
+++ b/examples/xnnpack/aot_compiler.py
@@ -87,14 +87,14 @@
 
     model = model.eval()
     # pre-autograd export. eventually this will become torch.export
-    ep = torch.export.export_for_training(model, example_inputs, strict=True)
+    ep = torch.export.export_for_training(model, example_inputs, strict=False)
     model = ep.module()
 
     if args.quantize:
         logging.info("Quantizing Model...")
         # TODO(T165162973): This pass shall eventually be folded into quantizer
         model = quantize(model, example_inputs, quant_type)
-        ep = torch.export.export_for_training(model, example_inputs, strict=True)
+        ep = torch.export.export_for_training(model, example_inputs, strict=False)
 
     edge = to_edge_transform_and_lower(
         ep,