diff --git a/comfy/model_management.py b/comfy/model_management.py
index 034799516..2a9f18068 100644
--- a/comfy/model_management.py
+++ b/comfy/model_management.py
@@ -954,7 +954,7 @@ def device_supports_non_blocking(device):
     if is_device_mps(device):
         return False #pytorch bug? mps doesn't support non blocking
     if is_intel_xpu(): #xpu does support non blocking but it is slower on iGPUs for some reason so disable by default until situation changes
-        return True
+        return False
     if args.deterministic: #TODO: figure out why deterministic breaks non blocking from gpu to cpu (previews)
         return False
     if directml_enabled: