diff --git a/gpt4all-backend/llama.cpp-mainline b/gpt4all-backend/llama.cpp-mainline
index d2e3b5fd..b0df9e6f 160000
--- a/gpt4all-backend/llama.cpp-mainline
+++ b/gpt4all-backend/llama.cpp-mainline
@@ -1 +1 @@
-Subproject commit d2e3b5fd464aa95d44b3aeb6d532ad7374f7478b
+Subproject commit b0df9e6fad734a4cff48e80b120b72f1f2c39094
diff --git a/gpt4all-chat/chatlistmodel.h b/gpt4all-chat/chatlistmodel.h
index 24a95c3d..3f99c622 100644
--- a/gpt4all-chat/chatlistmodel.h
+++ b/gpt4all-chat/chatlistmodel.h
@@ -196,6 +196,7 @@ public:
         m_newChat = nullptr;
         m_serverChat = nullptr;
         m_currentChat = nullptr;
+        for (auto * chat: m_chats) { delete chat; }
         m_chats.clear();
     }
 
diff --git a/gpt4all-chat/main.cpp b/gpt4all-chat/main.cpp
index d015581a..7debe8be 100644
--- a/gpt4all-chat/main.cpp
+++ b/gpt4all-chat/main.cpp
@@ -63,9 +63,11 @@ int main(int argc, char *argv[])
     }
 #endif
 
+    int res = app.exec();
+
     // Make sure ChatLLM threads are joined before global destructors run.
     // Otherwise, we can get a heap-use-after-free inside of llama.cpp.
     ChatListModel::globalInstance()->clearChats();
 
-    return app.exec();
+    return res;
 }