diff --git a/examples/llava/convert_image_encoder_to_gguf.py b/examples/llava/convert_image_encoder_to_gguf.py
index 2949faec421be..5920af48023e7 100644
--- a/examples/llava/convert_image_encoder_to_gguf.py
+++ b/examples/llava/convert_image_encoder_to_gguf.py
@@ -363,6 +363,11 @@ def get_non_negative_vision_feature_layers(v_hparams):
         else:
             data = data.squeeze().numpy().astype(np.float32)
 
+        # byteswaps v.head.ffn_up.bias for big-endian systems
+        # see: https://github.com/ggml-org/llama.cpp/issues/12863
+        if name == "v.head.ffn_up.bias" and args.bigendian:
+            data = data.byteswap(inplace=True)
+
         fout.add_tensor(name, data)
 
     print("Projector tensors added\n")