Home› Projects› MOSS-Video-Preview
MOSS-Video-Preview
Python

MOSS-Video-Preview

An 11B model for real-time video understanding with gated cross-attention and streaming inference

by OpenMOSS · GitHub
172
Stars
5
Forks
Apache-2.0
License
2026
Created
4 mo ago
Last commit
multimodal
Category
Python
Language
multimodalstreaming-videovideo-understandingApache-2.0Python
View on GitHub
In plain words

Explore real-time video understanding capabilities with a model designed for advanced video processing and reasoning.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
MOSS-Video-Preview — GitHub preview card
📈 Star history
172171
2026-09-242026-11-15
📈 Track MOSS-Video-Preview

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

An 11B model for real-time video understanding with gated cross-attention and streaming inference

MOSS-Video-Preview has 172 stars on GitHub. It has been forked 5 times. MOSS-Video-Preview is written mainly in Python. It has been in active development since 2026. MOSS-Video-Preview is available under the Apache-2.0 license. Its main topics are multimodal, streaming-video, video-understanding, vision-language-model.

❓ Frequently asked questions

What is MOSS-Video-Preview?

An 11B model for real-time video understanding with gated cross-attention and streaming inference

Is MOSS-Video-Preview open source?

MOSS-Video-Preview is an open-source project. It is released under the Apache-2.0 license.

Is MOSS-Video-Preview free?

Yes. MOSS-Video-Preview is free and open source — you can use, modify and self-host it.

What license does MOSS-Video-Preview use?

MOSS-Video-Preview is available under the Apache-2.0 license.

What language is MOSS-Video-Preview written in?

MOSS-Video-Preview is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — MOSS-Video-Preview

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=openmoss-moss-video-preview)](https://olud.ai/project/openmoss-moss-video-preview.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →
Chat-UniVi
[CVPR 2024 Highlight🔥] Chat-UniVi: Unified Visual Representation Empowers Large Language Models…
★ 945 · image-understanding
sharesvideo-understandingvision-language-model
Mage
★ 1.8k · computer-use
sharesstreaming-videovideo-understanding
t2v_metrics
Evaluating text-to-image/video/3D models with VQAScore
★ 600 · generative-ai
sharesvision-language-model
Qwen-VL
The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed b…
★ 6.7k · large-language-models
sharesvision-language-model
MOSS-VL
An open-weight 11B model series for long-form and real-time video understanding
★ 813 · llms
sharesstreaming-videovideo-understanding
RoboFlamingo
Code for RoboFlamingo
★ 437 · artificial-intelligence
sharesvision-language-model
video-understanding-dataset
A collection of recent video understanding datasets, under construction!
★ 469 · action-recognition
sharesvideo-understanding
MGM
Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"
★ 3.3k · generation
sharesvision-language-model
lmms-eval
One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
★ 4.5k · agi
sharesvideo-understandingvision-language-model
Senna
Bridging Large Vision-Language Models and End-to-End Autonomous Driving
★ 551 · autonomous-driving
sharesvision-language-model

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.