diff --git a/src/diffusers/pipeline_utils.py b/src/diffusers/pipeline_utils.py
index 5e7cf2d7a555..35996d65072c 100644
--- a/src/diffusers/pipeline_utils.py
+++ b/src/diffusers/pipeline_utils.py
@@ -169,10 +169,12 @@ def to(self, torch_device: Optional[Union[str, torch.device]] = None):
             module = getattr(self, name)
             if isinstance(module, torch.nn.Module):
                 if module.dtype == torch.float16 and str(torch_device) in ["cpu", "mps"]:
-                    raise ValueError(
-                        "Pipelines loaded with `torch_dtype=torch.float16` cannot be moved to `cpu` or `mps` "
-                        "due to the lack of support for `float16` operations on those devices in PyTorch. "
-                        "Please remove the `torch_dtype=torch.float16` argument, or use a `cuda` device."
+                    logger.warning(
+                        "Pipelines loaded with `torch_dtype=torch.float16` cannot run with `cpu` or `mps` device. It"
+                        " is not recommended to move them to `cpu` or `mps` as running them will fail. Please make"
+                        " sure to use a `cuda` device to run the pipeline in inference. due to the lack of support for"
+                        " `float16` operations on those devices in PyTorch. Please remove the"
+                        " `torch_dtype=torch.float16` argument, or use a `cuda` device to run inference."
                     )
                 module.to(torch_device)
         return self
diff --git a/tests/test_pipelines.py b/tests/test_pipelines.py
index e961378a9a58..567699986eb3 100644
--- a/tests/test_pipelines.py
+++ b/tests/test_pipelines.py
@@ -247,17 +247,6 @@ def to(self, device):
 
         return extract
 
-    def test_pipeline_fp16_cpu_error(self):
-        model = self.dummy_uncond_unet
-        scheduler = DDPMScheduler(num_train_timesteps=10)
-        pipe = DDIMPipeline(model.half(), scheduler)
-
-        if str(torch_device) in ["cpu", "mps"]:
-            self.assertRaises(ValueError, pipe.to, torch_device)
-        else:
-            # moving the pipeline to GPU should work
-            pipe.to(torch_device)
-
     def test_ddim(self):
         unet = self.dummy_uncond_unet
         scheduler = DDIMScheduler()