@azhuvath, which optimum-intel version do you use? please try to update it according to suggestion from:
openvinotoolkit/openvino.genai#1656 (comment)

@azhuvath, which optimum-intel version do you use? please try to update it according to suggestion from: openvinotoolkit/openvino.genai#1656 (comment)

It works now.

Should I create a different issue for Qwen2.5 as opposed to Qwen2VL
optimum-cli export openvino --model "Qwen/Qwen2.5-VL-7B-Instruct" --trust-remote-code --weight-format int4 "Qwen2.5-VL-7B-Instruct-OV-INT4"

(ov_env) PS C:\Users\devcloud\Desktop\Scribbler\Qwen2VL> optimum-cli export openvino --model "Qwen/Qwen2.5-VL-7B-Instruct" --trust-remote-code --weight-format int4 "Qwen2.5-VL-7B-Instruct-OV-INT4"
C:\Python310\lib\importlib\util.py:247: DeprecationWarning: The openvino.runtime module is deprecated and will be removed in the 2026.0 release. Please replace openvino.runtime with openvino.
self.spec.loader.exec_module(self)
config.json: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1.37k/1.37k [00:00<?, ?B/s]
Traceback (most recent call last):
File "C:\Users\devcloud\Desktop\Scribbler\Qwen2VL\ov_env\lib\site-packages\transformers\models\auto\configuration_auto.py", line 1034, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "C:\Users\devcloud\Desktop\Scribbler\Qwen2VL\ov_env\lib\site-packages\transformers\models\auto\configuration_auto.py", line 736, in getitem
raise KeyError(key)
KeyError: 'qwen2_5_vl'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Python310\lib\runpy.py", line 196, in _run_module_as_main
return _run_code(code, main_globals, None,
File "C:\Python310\lib\runpy.py", line 86, in run_code
exec(code, run_globals)
File "C:\Users\devcloud\Desktop\Scribbler\Qwen2VL\ov_env\Scripts\optimum-cli.exe_main.py", line 7, in
File "C:\Users\devcloud\Desktop\Scribbler\Qwen2VL\ov_env\lib\site-packages\optimum\commands\optimum_cli.py", line 208, in main
service.run()
File "C:\Users\devcloud\Desktop\Scribbler\Qwen2VL\ov_env\lib\site-packages\optimum\commands\export\openvino.py", line 454, in run
model = model_cls.from_pretrained(
File "C:\Users\devcloud\Desktop\Scribbler\Qwen2VL\ov_env\lib\site-packages\optimum\intel\openvino\modeling_base.py", line 469, in from_pretrained
return super().from_pretrained(
File "C:\Users\devcloud\Desktop\Scribbler\Qwen2VL\ov_env\lib\site-packages\optimum\modeling_base.py", line 416, in from_pretrained
config = cls._load_config(
File "C:\Users\devcloud\Desktop\Scribbler\Qwen2VL\ov_env\lib\site-packages\optimum\modeling_base.py", line 247, in _load_config
config = AutoConfig.from_pretrained(
File "C:\Users\devcloud\Desktop\Scribbler\Qwen2VL\ov_env\lib\site-packages\transformers\models\auto\configuration_auto.py", line 1036, in from_pretrained
raise ValueError(
ValueError: The checkpoint you are trying to load has model type qwen2_5_vl but Transformers does not recognize this architecture. This could be because of an issue with the checkpoint, or because your version of Transformers is out of date.

@azhuvath this issue shows that your installed transformers version does not support qwen2.5vl model yet

@eaidova I have tried latest Transformers with the following command pip install git+https://github.com/huggingface/transformers which have support for qwen2.5vl model. But iam getting the below error which is same as @azhuvath reported.

(qwen_env) C:\Users\snvx\Environments>optimum-cli export openvino --model Qwen/Qwen2.5-VL-3B-Instruct Qwen2.5-VL-3B-Instruct\INT4 --weight-format int4
C:\Users\snvx\AppData\Local\miniforge3\lib\importlib\util.py:247: DeprecationWarning: The `openvino.runtime` module is deprecated and will be removed in the 2026.0 release. Please replace `openvino.runtime` with `openvino`.
  self.__spec__.loader.exec_module(self)
Traceback (most recent call last):
  File "C:\Users\snvx\AppData\Local\miniforge3\lib\runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "C:\Users\snvx\AppData\Local\miniforge3\lib\runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "C:\Users\snvx\Environments\qwen_env\Scripts\optimum-cli.exe\__main__.py", line 7, in <module>
  File "C:\Users\snvx\Environments\qwen_env\lib\site-packages\optimum\commands\optimum_cli.py", line 208, in main
    service.run()
  File "C:\Users\snvx\Environments\qwen_env\lib\site-packages\optimum\commands\export\openvino.py", line 454, in run
    model = model_cls.from_pretrained(
  File "C:\Users\snvx\Environments\qwen_env\lib\site-packages\optimum\intel\openvino\modeling_base.py", line 469, in from_pretrained
    return super().from_pretrained(
  File "C:\Users\snvx\Environments\qwen_env\lib\site-packages\optimum\modeling_base.py", line 438, in from_pretrained
    return from_pretrained_method(
  File "C:\Users\snvx\Environments\qwen_env\lib\site-packages\optimum\intel\openvino\modeling_visual_language.py", line 620, in _from_transformers
    main_export(
  File "C:\Users\snvx\Environments\qwen_env\lib\site-packages\optimum\exporters\openvino\__main__.py", line 264, in main_export
    raise ValueError(
ValueError: Trying to export a qwen2-5-vl model, that is a custom or unsupported architecture, but no custom export configuration was passed as `custom_export_configs`. Please refer to https://huggingface.co/docs/optimum/main/en/exporters/onnx/usage_guides/export_a_model#custom-export-of-transformers-models for an example on how to export custom models. Please open an issue at https://github.com/huggingface/optimum-intel/issues if you would like the model type qwen2-5-vl to be supported natively in the OpenVINO export.

It looks like the optimum-intel package is not compatible with the latest transformers because i have below error when the latest transformers package is installed

ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
optimum-intel 1.22.0.dev0+f601b8b requires transformers<4.49,>=4.36, but you have transformers 4.49.0.dev0 which is incompatible.

@eaidova I have tried latest Transformers with the following command pip install git+https://github.com/huggingface/transformers which have support for qwen2.5vl model. But iam getting the below error which is same as @azhuvath reported.

(qwen_env) C:\Users\snvx\Environments>optimum-cli export openvino --model Qwen/Qwen2.5-VL-3B-Instruct Qwen2.5-VL-3B-Instruct\INT4 --weight-format int4
C:\Users\snvx\AppData\Local\miniforge3\lib\importlib\util.py:247: DeprecationWarning: The `openvino.runtime` module is deprecated and will be removed in the 2026.0 release. Please replace `openvino.runtime` with `openvino`.
  self.__spec__.loader.exec_module(self)
Traceback (most recent call last):
  File "C:\Users\snvx\AppData\Local\miniforge3\lib\runpy.py", line 196, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "C:\Users\snvx\AppData\Local\miniforge3\lib\runpy.py", line 86, in _run_code
    exec(code, run_globals)
  File "C:\Users\snvx\Environments\qwen_env\Scripts\optimum-cli.exe\__main__.py", line 7, in <module>
  File "C:\Users\snvx\Environments\qwen_env\lib\site-packages\optimum\commands\optimum_cli.py", line 208, in main
    service.run()
  File "C:\Users\snvx\Environments\qwen_env\lib\site-packages\optimum\commands\export\openvino.py", line 454, in run
    model = model_cls.from_pretrained(
  File "C:\Users\snvx\Environments\qwen_env\lib\site-packages\optimum\intel\openvino\modeling_base.py", line 469, in from_pretrained
    return super().from_pretrained(
  File "C:\Users\snvx\Environments\qwen_env\lib\site-packages\optimum\modeling_base.py", line 438, in from_pretrained
    return from_pretrained_method(
  File "C:\Users\snvx\Environments\qwen_env\lib\site-packages\optimum\intel\openvino\modeling_visual_language.py", line 620, in _from_transformers
    main_export(
  File "C:\Users\snvx\Environments\qwen_env\lib\site-packages\optimum\exporters\openvino\__main__.py", line 264, in main_export
    raise ValueError(
ValueError: Trying to export a qwen2-5-vl model, that is a custom or unsupported architecture, but no custom export configuration was passed as `custom_export_configs`. Please refer to https://huggingface.co/docs/optimum/main/en/exporters/onnx/usage_guides/export_a_model#custom-export-of-transformers-models for an example on how to export custom models. Please open an issue at https://github.com/huggingface/optimum-intel/issues if you would like the model type qwen2-5-vl to be supported natively in the OpenVINO export.

It looks like the optimum-intel package is not compatible with the latest transformers because i have below error when the latest transformers package is installed

ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
optimum-intel 1.22.0.dev0+f601b8b requires transformers<4.49,>=4.36, but you have transformers 4.49.0.dev0 which is incompatible.

meet the same error, is there a quick method to convert qwen2.5-vl model to openvino form via optimum?