diff --git a/src/llama-context.cpp b/src/llama-context.cpp
index 7f7b838e14..78f12011c4 100644
--- a/src/llama-context.cpp
+++ b/src/llama-context.cpp
@@ -1718,7 +1718,7 @@ uint32_t llama_context::output_reserve(int32_t n_outputs, const llama_batch & ba
         if (buf_output) {
 #ifndef NDEBUG
             // This doesn't happen often, but may be annoying in some cases (like the HellaSwag benchmark)
-            LLAMA_LOG_INFO("%s: reallocating output buffer from size %.02f MiB to %.02f MiB\n", __func__, prev_size / 1024.0 / 1024.0, new_size / 1024.0 / 1024.0);
+            LLAMA_LOG_DEBUG("%s: reallocating output buffer from size %.02f MiB to %.02f MiB\n", __func__, prev_size / 1024.0 / 1024.0, new_size / 1024.0 / 1024.0);
 #endif
             buf_output = nullptr;
             logits = nullptr;