diff --git a/python/sglang/srt/layers/moe/fused_moe_triton/layer.py b/python/sglang/srt/layers/moe/fused_moe_triton/layer.py
index c88aa4d2faa7..74558fd9b3ec 100644
--- a/python/sglang/srt/layers/moe/fused_moe_triton/layer.py
+++ b/python/sglang/srt/layers/moe/fused_moe_triton/layer.py
@@ -200,8 +200,7 @@ def __init__(
         self.quant_config = quant_config
         self.quant_method.create_weights(
             layer=self,
-            num_experts=self.num_experts,
-            num_local_experts=self.num_local_experts,
+            num_experts=self.num_local_experts,
             hidden_size=hidden_size,
             # FIXME: figure out which intermediate_size to use
             intermediate_size=self.intermediate_size_per_partition,
diff --git a/python/sglang/srt/layers/quantization/modelopt_quant.py b/python/sglang/srt/layers/quantization/modelopt_quant.py
index 64df434ae149..fca0ee38b9c0 100755
--- a/python/sglang/srt/layers/quantization/modelopt_quant.py
+++ b/python/sglang/srt/layers/quantization/modelopt_quant.py
@@ -752,7 +752,6 @@ def create_weights(
         self,
         layer: torch.nn.Module,
         num_experts: int,
-        num_local_experts: int,
         hidden_size: int,
         intermediate_size_per_partition: int,
         params_dtype: torch.dtype,
@@ -766,7 +765,7 @@ def create_weights(
 
         # TODO(ch-wan): check if this is needed
         layer.num_experts = num_experts
-        layer.num_local_experts = num_local_experts
+        layer.num_local_experts = num_experts
         layer.intermediate_size_per_partition = intermediate_size_per_partition
         layer.params_dtype = params_dtype
         layer.quant_config = self.quant_config