CASA-Qwen2_5-VL-3B-LiveCC

kyutai/CASA-Qwen2_5-VL-3B-LiveCC

Video Text To Text4.4B parameterstransformersLicense: cc-by-nc-sa-4.0

Tracked by OpenModelStats since September 5, 2026View on Hugging Face ↗

Downloads 30D: 2,426
Total downloads: 4,430
Gained 7D: 0; 0% vs baseline
Gained 30D: —
Likes: 6; +0 in 7D
Rank · tracked models: #19,457; 104(up 104 places)this week
Parameters: 4.4B
Last source update: Sep 6, 2026

7D 30D 90D 1Y All

Total downloads Gained per day Rolling recent downloads

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Overview

CASA-Qwen2_5-VL-3B-LiveCC is a video text to text model published by kyutai. OpenModelStats has tracked the model since Sep 5, 2026, most recently observing it Oct 1, 2026.

Published: Dec 18, 2025
Last updated: Sep 6, 2026
Library: transformers
License: cc-by-nc-sa-4.0
Task: Video Text To Text
Parameters: 4,404,943,872
Spaces: —
Derivative models: —
Velocity 7D/day: 0

transformerssafetensorsqwen2_5vl_cafeature-extractionvideo-text-to-textcustom_codeendataset:chenjoya/Live-WhisperX-526Karxiv:2512.19535base_model:Qwen/Qwen2.5-VL-3B-Instructbase_model:finetune:Qwen/Qwen2.5-VL-3B-Instructlicense:cc-by-nc-sa-4.0

Publisher

kyutaiView publisher statistics →

Derived from Qwen/Qwen2.5-VL-3B-Instruct (reported by the source; parent not yet tracked).

Similar models

Models similar to CASA-Qwen2_5-VL-3B-LiveCC
Model	Task	DL 30D	Likes	Params
TimeLens2-4BMCG-NJU	Video Text To Text	1,318	13	4.4B
VideoChat3-4BMCG-NJU	Video Text To Text	3,031	27	4.5B
Molmo2-VideoPoint-4Ballenai	Video Text To Text	199	22	4.9B
GenS-qwen2d5-vl-3byaolily	Video Text To Text	4,731	0	3.8B
Code-as-World-VL-4BMirroS-Lab	Video Text To Text	489	6	5.2B
UGC-VideoCaptioneropeninterx	Video Text To Text	1,405	4	5.5B