diff --git a/src/llmtuner/model/patcher.py b/src/llmtuner/model/patcher.py
index 5f67f618..c537a6d2 100644
--- a/src/llmtuner/model/patcher.py
+++ b/src/llmtuner/model/patcher.py
@@ -284,6 +284,12 @@ def patch_model(
     if is_trainable:
         _prepare_model_for_training(model, model_args)
 
+    if getattr(model.config, "model_type", None) == "mixtral" and is_deepspeed_zero3_enabled():
+        require_version("deepspeed>=0.13.0", "To fix: pip install deepspeed>=0.13.0")
+        from deepspeed.utils import set_z3_leaf_modules
+        from transformers.models.mixtral.modeling_mixtral import MixtralSparseMoeBlock
+        set_z3_leaf_modules(model, [MixtralSparseMoeBlock])
+
 
 def patch_valuehead_model(model: "AutoModelForCausalLMWithValueHead") -> None:
     def tie_weights(self: "AutoModelForCausalLMWithValueHead") -> None: