diff --git a/llama.cpp b/llama.cpp
index 0124e424f..0c9d3f745 100644
--- a/llama.cpp
+++ b/llama.cpp
@@ -2435,6 +2435,10 @@ struct llama_model_loader {
             mapping->unmap(0, mmap_first);
             mapping->unmap(mmap_last, mapping->size - mmap_last);
         }
+
+        if (progress_callback) {
+            progress_callback(1.0f, progress_callback_user_data);
+        }
     }
 };
 
@@ -3691,10 +3695,6 @@ static void llm_load_tensors(
 
     ml.load_all_data(ctx, progress_callback, progress_callback_user_data, buf_mmap, use_mlock ? &model.mlock_mmap : NULL);
 
-    if (progress_callback) {
-        progress_callback(1.0f, progress_callback_user_data);
-    }
-
     model.mapping = std::move(ml.mapping);
 
     // loading time will be recalculate after the first eval, so