diff --git a/convert_hf_to_gguf.py b/convert_hf_to_gguf.py
index 8db6ecbd11..78ad26c656 100755
--- a/convert_hf_to_gguf.py
+++ b/convert_hf_to_gguf.py
@@ -122,8 +122,8 @@ def parse_args() -> argparse.Namespace:
         help="Export only the multi-token prediction (MTP) head as a separate GGUF, suitable for use as a speculative draft. An 'mtp-' prefix will be added to the output file name.",
     )
     parser.add_argument(
-        "--no-mtp", action="store_true",
-        help="Exclude the multi-token prediction (MTP) head from the converted GGUF. Pair with --mtp on a second run to publish trunk and MTP as two files. Note: the split form duplicates embeddings, but even though the bundled default is more space-efficient overall, this allows differing quantization which may be more performant.",
+        "--no-nextn", "--no-mtp", dest="no_mtp", action="store_true",
+        help="Exclude NextN speculative draft tensors from the converted GGUF. Pair with --mtp or --dspark on a second run to publish target and draft as two files.",
     )
     parser.add_argument(
         "--dspark", action="store_true",
@@ -259,7 +259,7 @@ def main() -> None:
             model_class = MistralModel
 
         if sum((args.mtp, args.no_mtp, args.dspark)) > 1:
-            logger.error("--mtp, --no-mtp, and --dspark are mutually exclusive")
+            logger.error("--mtp, --no-nextn, and --dspark are mutually exclusive")
             sys.exit(1)
 
         if args.dspark:
@@ -271,7 +271,7 @@ def main() -> None:
 
         if args.mtp or args.no_mtp:
             if not model_class.supports_mtp_export:
-                logger.error("--mtp / --no-mtp are not supported for %s", model_architecture)
+                logger.error("--mtp / --no-nextn are not supported for %s", model_architecture)
                 sys.exit(1)
             if args.no_mtp:
                 model_class.no_mtp = True