diff --git a/src/llamafactory/data/template.py b/src/llamafactory/data/template.py
index 701cd239..84f41b11 100644
--- a/src/llamafactory/data/template.py
+++ b/src/llamafactory/data/template.py
@@ -1071,6 +1071,7 @@ register_template(
     stop_words=["<|im_end|>"],
     thought_words=("◁think▷", "◁/think▷"),
     mm_plugin=get_mm_plugin("kimi_vl", image_token="<|media_pad|>"),
+    template_class=ReasoningTemplate,
 )
 
 
@@ -1354,6 +1355,24 @@ register_template(
     template_class=ReasoningTemplate,
 )
 
+# copied from qwen2vl
+register_template(
+    name="mimo_vl",
+    format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
+    format_assistant=StringFormatter(slots=["{{content}}<|im_end|>\n"]),
+    format_system=StringFormatter(slots=["<|im_start|>system\n{{content}}<|im_end|>\n"]),
+    format_function=FunctionFormatter(slots=["{{content}}<|im_end|>\n"], tool_format="qwen"),
+    format_observation=StringFormatter(
+        slots=["<|im_start|>user\n<tool_response>\n{{content}}\n</tool_response><|im_end|>\n<|im_start|>assistant\n"]
+    ),
+    format_tools=ToolFormatter(tool_format="qwen"),
+    default_system="You are MiMo, an AI assistant developed by Xiaomi.",
+    stop_words=["<|im_end|>"],
+    replace_eos=True,
+    mm_plugin=get_mm_plugin(name="qwen2_vl", image_token="<|image_pad|>", video_token="<|video_pad|>"),
+    template_class=ReasoningTemplate,
+)
+
 
 # copied from chatml template
 register_template(
@@ -1695,15 +1714,9 @@ register_template(
 
 register_template(
     name="smollm2",
-    format_system=StringFormatter(
-        slots=["<|im_start|>system\n{{content}}<|im_end|>\n"]
-    ),
-    format_user=StringFormatter(
-        slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]
-    ),
-    format_assistant=StringFormatter(
-        slots=["{{content}}<|im_end|>\n"]
-    ),
+    format_system=StringFormatter(slots=["<|im_start|>system\n{{content}}<|im_end|>\n"]),
+    format_user=StringFormatter(slots=["<|im_start|>user\n{{content}}<|im_end|>\n<|im_start|>assistant\n"]),
+    format_assistant=StringFormatter(slots=["{{content}}<|im_end|>\n"]),
     stop_words=["<|im_end|>"],
     default_system="You are a helpful AI assistant named SmolLM, trained by Hugging Face.",
 )
diff --git a/src/llamafactory/extras/constants.py b/src/llamafactory/extras/constants.py
index 11b3319e..06e450c9 100644
--- a/src/llamafactory/extras/constants.py
+++ b/src/llamafactory/extras/constants.py
@@ -1460,6 +1460,22 @@ register_model_group(
 )
 
 
+register_model_group(
+    models={
+        "MiMo-7B-VL-Instruct": {
+            DownloadSource.DEFAULT: "XiaomiMiMo/MiMo-VL-7B-SFT",
+            DownloadSource.MODELSCOPE: "XiaomiMiMo/MiMo-VL-7B-SFT",
+        },
+        "MiMo-7B-VL-RL": {
+            DownloadSource.DEFAULT: "XiaomiMiMo/MiMo-VL-7B-RL",
+            DownloadSource.MODELSCOPE: "XiaomiMiMo/MiMo-VL-7B-RL",
+        },
+    },
+    template="mimo_vl",
+    multimodal=True,
+)
+
+
 register_model_group(
     models={
         "MiniCPM-2B-SFT-Chat": {