janhq / Jan-v2-VL-max-FP8
Agents31B11329Updated Dec 22, 2025
Downloads
113
Likes
29
Last updated
Dec 22, 2025
License
apache-2.0
Jan-v2-VL-max extends the Jan-v2-VL family to a 30B-parameter vision–language model focused on long-horizon execution. This release scales model capacity and applies LoRA-based RLVR to improve stability over many steps with low error accumulation. For evaluation, we continue t…
Tasks & library
- image text to text
- transformers
Tags
- transformers
- qwen3_vl_moe
- image-text-to-text
- agent
- conversational
- en
Technical specifications
Parameters31B
Librarytransformers
Languagesen
Base modelQwen/Qwen3-VL-30B-A3B-Thinking
Licenseapache-2.0
