diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py
index 336e843323..e660361094 100755
--- a/convert_hf_to_gguf.py
+++ b/convert_hf_to_gguf.py
@@ -1064,7 +1064,7 @@ class TextModel(ModelBase):
 
         # Skip multimodal tensors
         if name.startswith(("mlp", "vit.", "vpm.", "siglip2.", "conformer.", "merger.", "resampler.", "sound_encoder.", "sound_projection.")) \
-                or "visual." in name or "audio." in name or "talker." in name \
+                or "visual." in name or "vision." in name or "audio." in name or "talker." in name \
                 or "vision_" in name or "audio_" in name or "sam_model" in name \
                 or "token2wav." in name or "code2wav." in name \
                 or "projector." in name or "pre_mm_projector_norm" in name \