diff --git a/gpt4all-chat/chatllm.cpp b/gpt4all-chat/chatllm.cpp
index bf3f6253..750e8548 100644
--- a/gpt4all-chat/chatllm.cpp
+++ b/gpt4all-chat/chatllm.cpp
@@ -274,16 +274,6 @@ bool ChatLLM::loadModel(const ModelInfo &modelInfo)
     // Store the file info in the modelInfo in case we have an error loading
     m_llModelInfo.fileInfo = fileInfo;
 
-    // Check if we've previously tried to load this file and failed/crashed
-    if (MySettings::globalInstance()->attemptModelLoad() == filePath) {
-        MySettings::globalInstance()->setAttemptModelLoad(QString()); // clear the flag
-        if (!m_isServer)
-            LLModelStore::globalInstance()->releaseModel(m_llModelInfo); // release back into the store
-        m_llModelInfo = LLModelInfo();
-        emit modelLoadingError(QString("Previous attempt to load model resulted in crash for `%1` most likely due to insufficient memory. You should either remove this model or decrease your system RAM usage by closing other applications.").arg(modelInfo.filename()));
-        return false;
-    }
-
     if (fileInfo.exists()) {
         if (isChatGPT) {
             QString apiKey;
@@ -319,9 +309,6 @@ bool ChatLLM::loadModel(const ModelInfo &modelInfo)
                     return m_shouldBeLoaded;
                 });
 
-                // Update the settings that a model is being loaded and update the device list
-                MySettings::globalInstance()->setAttemptModelLoad(filePath);
-
                 // Pick the best match for the device
                 QString actualDevice = m_llModelInfo.model->implementation().buildVariant() == "metal" ? "Metal" : "CPU";
                 const QString requestedDevice = MySettings::globalInstance()->device();
@@ -373,7 +360,6 @@ bool ChatLLM::loadModel(const ModelInfo &modelInfo)
                     emit reportFallbackReason("<br>model or quant has no GPU support");
                 }
 
-                MySettings::globalInstance()->setAttemptModelLoad(QString());
                 if (!success) {
                     delete m_llModelInfo.model;
                     m_llModelInfo.model = nullptr;
diff --git a/gpt4all-chat/mysettings.cpp b/gpt4all-chat/mysettings.cpp
index f9774bde..9e5cdad0 100644
--- a/gpt4all-chat/mysettings.cpp
+++ b/gpt4all-chat/mysettings.cpp
@@ -717,24 +717,3 @@ void MySettings::setNetworkUsageStatsActive(bool b)
     setting.sync();
     emit networkUsageStatsActiveChanged();
 }
-
-QString MySettings::attemptModelLoad() const
-{
-    QSettings setting;
-    setting.sync();
-    return setting.value("attemptModelLoad", QString()).toString();
-}
-
-void MySettings::setAttemptModelLoad(const QString &modelFile)
-{
-    if (attemptModelLoad() == modelFile)
-        return;
-
-    QSettings setting;
-    if (modelFile.isEmpty())
-        setting.remove("attemptModelLoad");
-    else
-        setting.setValue("attemptModelLoad", modelFile);
-    setting.sync();
-    emit attemptModelLoadChanged();
-}
diff --git a/gpt4all-chat/mysettings.h b/gpt4all-chat/mysettings.h
index 4bfbef6b..c5019b91 100644
--- a/gpt4all-chat/mysettings.h
+++ b/gpt4all-chat/mysettings.h
@@ -110,8 +110,6 @@ public:
     bool networkUsageStatsActive() const;
     void setNetworkUsageStatsActive(bool b);
 
-    QString attemptModelLoad() const;
-    void setAttemptModelLoad(const QString &modelFile);
 
     QVector<QString> deviceList() const;
     void setDeviceList(const QVector<QString> &deviceList);