diff --git a/llama_stack/providers/inline/post_training/torchtune/recipes/lora_finetuning_single_device.py b/llama_stack/providers/inline/post_training/torchtune/recipes/lora_finetuning_single_device.py
index 7543b1f4e..80e206ebb 100644
--- a/llama_stack/providers/inline/post_training/torchtune/recipes/lora_finetuning_single_device.py
+++ b/llama_stack/providers/inline/post_training/torchtune/recipes/lora_finetuning_single_device.py
@@ -4,6 +4,7 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
+import gc
 import logging
 import os
 import time
@@ -580,6 +581,12 @@ class LoraFinetuningSingleDevice:
                 checkpoint.training_metrics = training_metrics
             checkpoints.append(checkpoint)
 
+        # clean up the memory after training finishes
+        self._model.to("cpu")
+        del self._model
+        gc.collect()
+        torch.cuda.empty_cache()
+
         return (memory_stats, checkpoints)
 
     async def validation(self) -> Tuple[float, float]: