MOSS-VL-Realtime
Open in the interactive archive →
Overview
Open-source 11B vision-language model (~22.7GB) built for real-time streaming video that proactively speaks up or deliberately stays silent...
Details
- Vendor
- OpenMOSS
- Type
- Multimodal LLM
- Release year
- 2026
- Jurisdiction
- China
- CEO
- N/A (academic lab — Fudan University; lead: Xipeng Qiu)
- Deployment
- Open weights (Hugging Face) + GitHub
- Open source
- Yes
- Free tier
- Yes
- Stock status
- N/A (academic)
- X
- @MosiAI_Official
Known safety issues
None publicly documented
AIDb Rating
AIDb v2.0 (curated): Capability 6/10 · Currency 10/10 · Access 8/10 · Significance 5/10 → 6.95
Last verified 2026-08-09 · Primary source ↗
Cite this
“MOSS-VL-Realtime.” AIDb — The AI Database. Verified 2026-08-09. https://theaidatabase.com/m/openmoss-moss-vl-realtime.html