diff --git a/interleaved_generation.py b/interleaved_generation.py
index dc17ccb..16dea40 100644
--- a/interleaved_generation.py
+++ b/interleaved_generation.py
@@ -62,12 +62,17 @@ def split_token_sequence(
 def main(args: argparse.Namespace):
     """Main function to generate and process model output."""
     # Load Chameleon model
-    model = ChameleonInferenceModel(
+    unquantized_model = ChameleonInferenceModel(
         MODEL_7B_PATH.as_posix(),
         TOKENIZER_TEXT_PATH.as_posix(),
         TOKENIZER_IMAGE_CFG_PATH.as_posix(),
         TOKENIZER_IMAGE_PATH.as_posix(),
     )
+    model = torch.quantization.quantize_dynamic(
+        unquantized_model,  # The model to be quantized
+        {torch.nn.Linear, torch.nn.LSTM},  # Layers to be dynamically quantized
+        dtype=torch.qint8  # Data type for quantization
+    )
     # Print model configuration
     print(f"Model path: {MODEL_7B_PATH}")
     print(f"Text tokenizer path: {TOKENIZER_TEXT_PATH}")
diff --git a/text2image.py b/text2image.py
index 53f3bcb..918ccf8 100644
--- a/text2image.py
+++ b/text2image.py
@@ -20,13 +20,17 @@ def main(args: argparse.Namespace):
     print(f"Batch size: {args.batch_size}")
     
     # Load Chameleon model
-    model = ChameleonInferenceModel(
+    unquantized_model = ChameleonInferenceModel(
         MODEL_7B_PATH.as_posix(),
         TOKENIZER_TEXT_PATH.as_posix(),
         TOKENIZER_IMAGE_CFG_PATH.as_posix(),
         TOKENIZER_IMAGE_PATH.as_posix(),
     )
-    
+    model = torch.quantization.quantize_dynamic(
+        unquantized_model,  # The model to be quantized
+        {torch.nn.Linear, torch.nn.LSTM},  # Layers to be dynamically quantized
+        dtype=torch.qint8  # Data type for quantization
+    )
     # Generate options
     options = Options()
     options.txt = False