CoME-VL

MBZUAI/CoME-VL

Image Text to TexttransformersLicense: apache-2.0

Tracked by OpenModelStats since September 7, 2026View on Hugging Face ↗

Downloads 30D: 16
Total downloads: 146
Gained 7D: +6(increase)
Gained 30D: —
Likes: 5; +0 in 7D
Rank · tracked models: —; –this week
Parameters: —
Last source update: Jul 11, 2026

CoME-VL gained 6 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 2026-09-07. Charts appear as daily observations accumulate.

Overview

CoME-VL is a image text to text model published by MBZUAI. OpenModelStats has tracked the model since Sep 7, 2026, most recently observing it Oct 6, 2026.

Published: Apr 1, 2026
Last updated: Jul 11, 2026
Library: transformers
License: apache-2.0
Task: Image Text to Text
Parameters: —
Spaces: 0
Derivative models: —
Velocity 7D/day: 1

transformersmultimodalchartsdiagramspointinglocalizationCoME-VLimage-text-to-textenarxiv:2604.03231base_model:Qwen/Qwen2-7Bbase_model:finetune:Qwen/Qwen2-7B

Publisher

MBZUAIView publisher statistics →

Model family

Based on base-model relationships reported by the source's metadata.

Base model

Qwen2-7B196K

Sibling models

Qwen2-7B-Instruct292.7K
qwen2-7b39

Similar models

Models similar to CoME-VL
Model	Task	DL 30D	Likes	Params
gemma-4-26B-A4B-itgoogle	Image Text to Text	12.6M	1,603	25.8B
Qwen3-VL-8B-InstructQwen	Image Text to Text	11.1M	1,167	8.8B
gemma-4-31B-itgoogle	Image Text to Text	9.6M	4,040	31.3B
Qwen3.5-9BQwen	Image Text to Text	8.8M	2,108	9.7B
Qwen3.5-4BQwen	Image Text to Text	8M	1,019	4.7B
Qwen3.8-27BQwen	Image Text to Text	6.8M	17.1K	27.8B