diff --git a/examples/server/server.cpp b/examples/server/server.cpp
index 2bf4026d5..55c1d4129 100644
--- a/examples/server/server.cpp
+++ b/examples/server/server.cpp
@@ -673,6 +673,8 @@ struct server_context {
             llama_free_model(model);
             model = nullptr;
         }
+
+        llama_batch_free(batch);
     }
 
     bool load_model(const gpt_params & params_) {