Unsupported qwen3_vl

[guweixin]

I tried quantizing the Qwen/Qwen3-VL-4B-Instruct using the below command
optimum-cli export openvino --model Qwen/Qwen3-VL-4B-Instruct Qwen3-VL-4B-Instruct-int4-sym_group-1 --task image-text-to-text --weight-format int4 --trust-remote-code --sym --backup-precision int8_sym --group-size -1
I tried inferring the quantized model using openvino.genai VLM example and getting the below error.
Unsupported 'qwen3_vl' VLM model type

[Wovchena]

GenAi doesn't support Qwen/Qwen3-VL-4B-Instruct. You are going to get the same error for non quantized model

[Wovchena]

CVS-176404

[feilonguu]

The 2026.0.0 development version of OpenVINO now supports Qwen3 VL 8B. May I ask when OpenVINO.GenAI will support Qwen3 VL 8B? Thank you!

[Wovchena]

Here's the draft #3253