OmniFysics-Captioner

Fysics-AI/OmniFysics-Captioner

Video Text To Text31.7B parameterstransformersLicense: other

Tracked by OpenModelStats since September 11, 2026View on Hugging Face ↗

Downloads 30D: 187
Total downloads: 187
Gained 7D: +34(increase)
Gained 30D: —
Likes: 3; +1 in 7D
Rank · tracked models: —; –this week
Parameters: 31.7B
Last source update: Sep 21, 2026

OmniFysics-Captioner gained 34 downloads during the last seven tracked days.

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

Not enough tracked history yet for a chart.

OpenModelStats began tracking this model on 2026-09-11. Charts appear as daily observations accumulate.

Overview

OmniFysics-Captioner is a video text to text model published by Fysics-AI. OpenModelStats has tracked the model since Sep 11, 2026, most recently observing it Sep 23, 2026.

Published: Aug 24, 2026
Last updated: Sep 21, 2026
Library: transformers
License: other
Task: Video Text To Text
Parameters: 31,719,205,488
Spaces: —
Derivative models: —
Velocity 7D/day: 5

transformerssafetensorsqwen3_omni_moetext-to-audiovideo-captioningmultimodalphysical-reasoninggrounded-generationphysicsvideo-text-to-textenlicense:other

Publisher

Fysics-AIView publisher statistics →

Similar models

Models similar to OmniFysics-Captioner
Model	Task	DL 30D	Likes	Params
cogvlm2-llama3-captionzai-org	Video Text To Text	233	119	12.5B
MOSS-VL-RealtimeOpenMOSS-Team	Video Text To Text	1,381	111	11.3B
MOSS-VL-Instruct-0408OpenMOSS-Team	Video Text To Text	775	107	11.3B
MOSS-VL-Instruct-0708OpenMOSS-Team	Video Text To Text	525	31	11.3B
MOSS-VL-Instruct-0708-FP8OpenMOSS-Team	Video Text To Text	474	21	11.3B
MOSS-VL-Realtime-NF4OpenMOSS-Team	Video Text To Text	427	15	11.3B