diff --git a/quark/torch/quantization/config/algo_configs.py b/quark/torch/quantization/config/algo_configs.py
index 4f258213f..a376ed3e5 100755
--- a/quark/torch/quantization/config/algo_configs.py
+++ b/quark/torch/quantization/config/algo_configs.py
@@ -561,6 +561,21 @@
         ],
         model_decoder_layers="model.language_model.layers",
     ),
+    "gemma4": GPTQConfig(
+        inside_layer_modules=[
+            "self_attn.k_proj",
+            "self_attn.v_proj",
+            "self_attn.q_proj",
+            "self_attn.o_proj",
+            "mlp.up_proj",
+            "mlp.gate_proj",
+            "mlp.down_proj",
+            "experts.*.up_proj",
+            "experts.*.gate_proj",
+            "experts.*.down_proj",
+        ],
+        model_decoder_layers="model.language_model.layers",
+    ),
     "gpt_oss": GPTQConfig(
         inside_layer_modules=[
             "self_attn.q_proj",
diff --git a/quark/torch/quantization/config/template.py b/quark/torch/quantization/config/template.py
index 99a040a37..373e29927 100644
--- a/quark/torch/quantization/config/template.py
+++ b/quark/torch/quantization/config/template.py
@@ -710,6 +710,7 @@ def get(cls, model_type: str) -> LLMTemplate:
             - gemma2
             - gemma3
             - gemma3_text
+            - gemma4
             - glm4_moe
             - glm4_moe_lite
             - glm_moe_dsa
@@ -1096,6 +1097,31 @@ def _set_layer_type_config(self, config: QConfig, layer_type_config: dict[type[n
         "q_layer_name": "*q_proj",
         "exclude_layers_name": ["*lm_head"],
     },
+    "gemma4": {
+        "kv_layers_name": ["*language_model.*k_proj", "*language_model.*v_proj"],
+        "q_layer_name": "*language_model.*q_proj",
+        "exclude_layers_name": [
+            "*vision_tower*",
+            "*embed_vision*",
+            "*audio_tower*",
+            "*embed_audio*",
+            "*multi_modal_projector*",
+            "*lm_head",
+            "*router.proj",
+        ],
+        "f2f_weight_converters": [
+            WeightConverter(
+                "gate_up_proj",
+                ["gate_proj.weight", "up_proj.weight"],
+                operations=[SplitFusedExperts(split_axis=0)],
+            ),
+            WeightConverter(
+                "down_proj",
+                ["down_proj.weight"],
+                operations=[SplitFusedExperts(split_axis=0)],
+            ),
+        ],
+    },
     "glm4_moe": {
         "kv_layers_name": ["*k_proj", "*v_proj"],
         "q_layer_name": "*q_proj",