Echo9Zulu/Qwen3-VL-4B-Instruct-int4_asym-ov

This model was converted to openvino IR format using the optimum-cli command line tool.

• —Language model weights are in int4
• —input/output embeddings on language model are int8
• —vision encoder in int8
• —calibration dataset applied during vision encoder quantization using optimum-intel defaults.