diff --git a/examples/sparse_2of4_quantization_fp8/llama3_8b_2of4.py b/examples/sparse_2of4_quantization_fp8/llama3_8b_2of4.py
index 21cec66c8b..85cb388679 100644
--- a/examples/sparse_2of4_quantization_fp8/llama3_8b_2of4.py
+++ b/examples/sparse_2of4_quantization_fp8/llama3_8b_2of4.py
@@ -116,7 +116,5 @@ def get_recipe(fp8_enabled):
 print("==========================================\n")
 
 # Save compressed model and tokenizer
-model.save_pretrained(
-    save_dir, save_compressed=args.fp8, disable_sparse_compression=True
-)
+model.save_pretrained(save_dir, save_compressed=args.fp8)
 tokenizer.save_pretrained(save_dir)
diff --git a/tests/e2e/vLLM/configs/sparse_24.yaml b/tests/e2e/vLLM/configs/sparse_24.yaml
index 653168b977..d0805a1b0d 100644
--- a/tests/e2e/vLLM/configs/sparse_24.yaml
+++ b/tests/e2e/vLLM/configs/sparse_24.yaml
@@ -5,4 +5,4 @@ recipe: tests/e2e/vLLM/recipes/Sparse_2of4/recipe_sparse_2of4.yaml
 scheme: sparse2of4_only
 dataset_id: HuggingFaceH4/ultrachat_200k
 dataset_split: train_sft
-save_compressed: False
\ No newline at end of file
+save_compressed: True
\ No newline at end of file