Rex-Omni

IDEA-Research/Rex-Omni

Image Text to Text4.1B parameterstransformersLicense: other
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
17.7K
Total downloads
349.9K
Gained 7D
Gained 30D
Likes
63
Rank · tracked models
#5,676
this week
Parameters
4.1B
Last source update
Oct 16, 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

Rex-Omni is a image text to text model published by IDEA-Research. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it 3h ago.

Published
Oct 9, 2025
Last updated
Oct 16, 2025
Library
transformers
License
other
Task
Image Text to Text
Parameters
4,065,787,904
Spaces
Derivative models
Velocity 7D/day
transformerssafetensorsqwen2_5_vlimage-text-to-textvisionobject-detectionmultimodalocrkeypoint-detectionvisual-promptingopen-set-detectionobject-pointing

Publisher

IDEA-ResearchView publisher statistics →

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

Similar models