Modelpublic

zenlm/zen-vl-4b-instruct

sourceHugging Faceapache-2.0updated 3mo agoView on Hugging Face

0likes21downloads

Model Card

Status: Superseded by zenlm/zen3-vl. Weights remain available for reproducibility.

zen-vl-4b-instruct

Superseded by zenlm/zen3-vl — canonical name.

Vision-language model for image understanding, OCR, and visual reasoning (4B (dense)).

Repackaged from Qwen/Qwen3-VL-4B-Instruct (apache-2.0, Alibaba Qwen). Not trained from scratch — a permissively-licensed redistribution for the OSS-clean Zen model line.

Specs

Property	Value
Parameters	4B (dense)
Architecture	Qwen3-VL
Modality	text + image + video

License

apache-2.0. Upstream: Qwen/Qwen3-VL-4B-Instruct by Alibaba Qwen (apache-2.0).