VideoLLaMA3-2B

DAMO-NLP-SG/VideoLLaMA3-2B

Video Text To Text2B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
2,688
Total downloads
116.2K
Gained 7D
Gained 30D
Likes
21
Rank · tracked models
#14,530
this week
Parameters
2B
Last source update
Sep 3, 2025

Downloads over time

Daily gain between consecutive observations

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.

Likes over time

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.

Rank among tracked models

Lower is better

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-08-24. Charts appear as daily observations accumulate.

Overview

VideoLLaMA3-2B is a video text to text model published by DAMO-NLP-SG. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 1h ago.

Published
Jan 21, 2025
Last updated
Sep 3, 2025
Library
transformers
License
apache-2.0
Task
Video Text To Text
Parameters
1,959,993,584
Spaces
Derivative models
Velocity 7D/day
transformerssafetensorsvideollama3_qwen2text-generationmulti-modallarge-language-modelvideo-language-modelvideo-text-to-textcustom_codeendataset:lmms-lab/LLaVA-OneVision-Datadataset:allenai/pixmo-docs

Publisher

DAMO-NLP-SGView publisher statistics →

Derived from DAMO-NLP-SG/VideoLLaMA3-2B-Image (reported by the source; parent not yet tracked).

Similar models

Models similar to VideoLLaMA3-2B
ModelDL 30D
Marlin-2BNemoStation6,648
Marlin-2B-ungatedlunahr2,309
VideoChat3-4BMCG-NJU2,973
Spatial-MLLM-v1.1-Instruct-135KDiankun2,751
LLaVA-NeXT-Video-7Blmms-lab226
LLaVA-NeXT-Video-7B-hfllava-hf119.2K