diff --git a/tensorrt_llm/_torch/model_config.py b/tensorrt_llm/_torch/model_config.py
index 232d2ccecd6..2ab19e1e787 100644
--- a/tensorrt_llm/_torch/model_config.py
+++ b/tensorrt_llm/_torch/model_config.py
@@ -344,7 +344,8 @@ def get_bindings_model_config(self,
                 architectures = self.pretrained_config.architectures
                 if len(architectures
                        ) == 1 and architectures[0] == "DeciLMForCausalLM":
-                    mlp_hidden_size = self._infer_nemotron_ffn_mult()
+                    mlp_hidden_size = self._infer_nemotron_ffn_mult(
+                    ) // self.mapping.tp_size
                 else:
                     raise ValueError(
                         f"Inferring mlp hidden size for model architecture: {architectures} isn't supported yet"