diff --git a/gpt4all-chat/chatllm.cpp b/gpt4all-chat/chatllm.cpp
index 58d68e60..4ae8c843 100644
--- a/gpt4all-chat/chatllm.cpp
+++ b/gpt4all-chat/chatllm.cpp
@@ -275,7 +275,7 @@ bool ChatLLM::loadModel(const ModelInfo &modelInfo)
                 if (requestedDevice != "CPU") {
                     const size_t requiredMemory = m_llModelInfo.model->requiredMem(filePath.toStdString());
                     std::vector<LLModel::GPUDevice> availableDevices = m_llModelInfo.model->availableGPUDevices(requiredMemory);
-                    if (!availableDevices.empty() && requestedDevice == "Auto") {
+                    if (!availableDevices.empty() && requestedDevice == "Auto" && devices.front().type == 2 /*a discrete gpu*/) {
                         m_llModelInfo.model->initializeGPUDevice(devices.front());
                     } else {
                         for (LLModel::GPUDevice &d : availableDevices) {