Zen3 VL family
Collection
Vision-language models. • 7 items • Updated
Status: Superseded by zenlm/zen3-vl. Weights remain available for reproducibility.
zen-vl-30b-agent
Superseded by zenlm/zen3-vl — canonical name.
Vision-language agent model for image understanding, OCR, and visual reasoning (30B total / 3B active (MoE)).
Repackaged from Qwen/Qwen3-VL-30B-A3B-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 | 30B total / 3B active (MoE) |
| Architecture | Qwen3-VL |
| Modality | text + image + video |
License
apache-2.0. Upstream: Qwen/Qwen3-VL-30B-A3B-Instruct by Alibaba Qwen (apache-2.0).
- Downloads last month
- 49
Model tree for zenlm/zen-vl-30b-agent
Base model
Qwen/Qwen3-VL-30B-A3B-Instruct