diff --git a/docs/models/supported_models.md b/docs/models/supported_models.md
index dbbbc5122b80..a24fa4bcce33 100644
--- a/docs/models/supported_models.md
+++ b/docs/models/supported_models.md
@@ -615,7 +615,7 @@ These models primarily accept the [`LLM.generate`](./generative_models.md#llmgen
 | `Gemma3nForConditionalGeneration` | Gemma 3n | T + I + A | `google/gemma-3n-E2B-it`, `google/gemma-3n-E4B-it`, etc. | | | ✅︎ |
 | `GLM4VForCausalLM`<sup>^</sup> | GLM-4V | T + I | `zai-org/glm-4v-9b`, `zai-org/cogagent-9b-20241220`, etc. | ✅︎ | ✅︎ | ✅︎ |
 | `Glm4vForConditionalGeneration` | GLM-4.1V-Thinking | T + I<sup>E+</sup> + V<sup>E+</sup> | `zai-org/GLM-4.1V-9B-Thinking`, etc. | ✅︎ | ✅︎ | ✅︎ |
-| `Glm4vMoeForConditionalGeneration` | GLM-4.5V | T + I<sup>E+</sup> + V<sup>E+</sup> | `zai-org/GLM-4.5V`, etc. | | ✅︎ | ✅︎ |
+| `Glm4vMoeForConditionalGeneration` | GLM-4.5V | T + I<sup>E+</sup> + V<sup>E+</sup> | `zai-org/GLM-4.5V`, etc. | ✅︎ | ✅︎ | ✅︎ |
 | `GraniteSpeechForConditionalGeneration` | Granite Speech | T + A | `ibm-granite/granite-speech-3.3-8b` | ✅︎ | ✅︎ | ✅︎ |
 | `H2OVLChatModel` | H2OVL | T + I<sup>E+</sup> | `h2oai/h2ovl-mississippi-800m`, `h2oai/h2ovl-mississippi-2b`, etc. | | ✅︎ | ✅︎ |
 | `Idefics3ForConditionalGeneration` | Idefics3 | T + I | `HuggingFaceM4/Idefics3-8B-Llama3`, etc. | ✅︎ | | ✅︎ |
diff --git a/vllm/model_executor/models/glm4_moe.py b/vllm/model_executor/models/glm4_moe.py
index 131c042c3c2d..aff491f9596c 100644
--- a/vllm/model_executor/models/glm4_moe.py
+++ b/vllm/model_executor/models/glm4_moe.py
@@ -41,7 +41,6 @@
 from vllm.model_executor.layers.layernorm import RMSNorm
 from vllm.model_executor.layers.linear import (MergedColumnParallelLinear,
                                                QKVParallelLinear,
-                                               ReplicatedLinear,
                                                RowParallelLinear)
 from vllm.model_executor.layers.logits_processor import LogitsProcessor
 from vllm.model_executor.layers.quantization import QuantizationConfig
@@ -118,14 +117,15 @@ def __init__(
         if config.hidden_act != "silu":
             raise ValueError(f"Unsupported activation: {config.hidden_act}. "
                              "Only silu is supported for now.")
-
-        self.gate = ReplicatedLinear(config.hidden_size,
-                                     config.n_routed_experts,
-                                     bias=False,
-                                     quant_config=None,
-                                     params_dtype=torch.float32,
-                                     prefix=f"{prefix}.gate")
-
+        # NOTE In the transformers implementation, the gate isn't an nn.Linear,
+        # so we cannot use ReplicatedLinear here.
+        # See: https://github.com/huggingface/transformers/blob/v4.55.1/src/transformers/models/glm4_moe/modeling_glm4_moe.py#L260
+        self.gate = nn.Linear(
+            config.hidden_size,
+            config.n_routed_experts,
+            bias=False,
+            dtype=torch.float32,
+        )
         self.gate.e_score_correction_bias = nn.Parameter(
             torch.empty(config.n_routed_experts, dtype=torch.float32))
 
@@ -181,7 +181,7 @@ def forward(self, hidden_states: torch.Tensor) -> torch.Tensor:
 
         if self.n_shared_experts is not None:
             shared_output = self.shared_experts(hidden_states)
-        router_logits, _ = self.gate(hidden_states.to(dtype=torch.float32))
+        router_logits = self.gate(hidden_states.to(dtype=torch.float32))
         final_hidden_states = self.experts(
             hidden_states=hidden_states,
             router_logits=router_logits) * self.routed_scaling_factor