diff --git a/unsloth/models/llama.py b/unsloth/models/llama.py
index 14ee5ee24e..496d566075 100644
--- a/unsloth/models/llama.py
+++ b/unsloth/models/llama.py
@@ -3735,4 +3735,17 @@ def _for_training(m):
 
 from .rl import PatchFastRL
 
+# Auto-enable grouped-GEMM MoE (tf<5 ModuleList experts) on built / PEFT'd models. Wrap the
+# loader leaves before PatchFastRL so downstream patchers see the wrapped versions. Guarded.
+try:
+    from unsloth_zoo.temporary_patches.moe_grouped_modulelist import wrap_loader_for_grouped_moe
+    FastLlamaModel.from_pretrained = staticmethod(
+        wrap_loader_for_grouped_moe(FastLlamaModel.from_pretrained)
+    )
+    FastLlamaModel.get_peft_model = staticmethod(
+        wrap_loader_for_grouped_moe(FastLlamaModel.get_peft_model)
+    )
+except Exception:
+    pass
+
 PatchFastRL(FastLanguageModel = FastLlamaModel)
diff --git a/unsloth/models/loader.py b/unsloth/models/loader.py
index 562afdd645..a56829a516 100644
--- a/unsloth/models/loader.py
+++ b/unsloth/models/loader.py
@@ -876,6 +876,15 @@ def from_pretrained(
             )
             # Patch it as well!
             model = dispatch_model.patch_peft_model(model, use_gradient_checkpointing)
+            # Re-evaluate grouped MoE now the adapter is attached: an expert-LoRA block falls back
+            # to the original loop, an attention-only adapter keeps the grouped path. Guarded.
+            try:
+                from unsloth_zoo.temporary_patches.moe_grouped_modulelist import (
+                    auto_enable_grouped_moe,
+                )
+                auto_enable_grouped_moe(model)
+            except Exception:
+                pass  # optional speedup; never block model loading
 
         # Patch Tiled MLP
         # to turn on set UNSLOTH_TILED_MLP to "arctic", "target", or "target:{GB}""
diff --git a/unsloth/models/vision.py b/unsloth/models/vision.py
index bdc2bd9ef6..852cfb9a3e 100644
--- a/unsloth/models/vision.py
+++ b/unsloth/models/vision.py
@@ -2119,3 +2119,16 @@ def check_dataset_for_missing_videos(
         warnings.warn(error_msg, stacklevel = 2)
 
     return missing
+
+
+# Auto-enable grouped-GEMM MoE (transformers<5 ModuleList experts); see llama.py.
+try:
+    from unsloth_zoo.temporary_patches.moe_grouped_modulelist import wrap_loader_for_grouped_moe
+    FastBaseModel.from_pretrained = staticmethod(
+        wrap_loader_for_grouped_moe(FastBaseModel.from_pretrained)
+    )
+    FastBaseModel.get_peft_model = staticmethod(
+        wrap_loader_for_grouped_moe(FastBaseModel.get_peft_model)
+    )
+except Exception:
+    pass