MOSS-VL-Base-0708

OpenMOSS-Team/MOSS-VL-Base-0708

Video Text To Text11.3B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since September 7, 2026View on Hugging Face ↗
Downloads 30D
79
Total downloads
230
Gained 7D
0
Gained 30D
—
Likes
18
+0 in 7D
Rank · tracked models
#47,902
485(down 485 places)this week
Parameters
11.3B
Last source update
Sep 23, 2026
Momentum
5.5
  • It moved from #49 to #51 among tracked Video Text To Text models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

MOSS-VL-Base-0708 is a video text to text model published by OpenMOSS-Team. OpenModelStats has tracked the model since Sep 7, 2026, most recently observing it Sep 23, 2026.

Published
Jul 13, 2026
Last updated
Sep 23, 2026
Library
transformers
License
apache-2.0
Task
Video Text To Text
Parameters
11,336,371,208
Spaces
—
Derivative models
—
Velocity 7D/day
0
transformerssafetensorsmoss_vlfeature-extractionBaseVideo-UnderstandingImage-UnderstandingMOSS-VLOpenMOSSmultimodalvideovision-language

Similar models

Models similar to MOSS-VL-Base-0708
ModelDL 30D
MOSS-VL-Instruct-0708-FP8OpenMOSS-Team1,548
MOSS-VL-RealtimeOpenMOSS-Team1,357
MOSS-VL-Instruct-0708OpenMOSS-Team873
MOSS-VL-Instruct-0408OpenMOSS-Team591
MOSS-VL-Realtime-NF4OpenMOSS-Team308
MOSS-VL-Base-0408OpenMOSS-Team135
OpenMOSS-Team/MOSS-VL-Base-0708 — Downloads, Growth & Stats | OpenModelStats