Qwen2.5-VL-3B-Instruct

Qwen/Qwen2.5-VL-3B-Instruct

Image Text to Text3.8B parameterstransformers
Tracked by OpenModelStats since September 6, 2026View on Hugging Face ↗
Downloads 30D
2.3M
Total downloads
103.4M
Gained 7D
+579.1K(increase)
0.6%(up) vs baseline
Gained 30D
—
Likes
711
+6 in 7D
Rank · tracked models
#167
–this week
Parameters
3.8B
Last source update
Apr 6, 2025
Momentum
85.9
  • Qwen2.5-VL-3B-Instruct gained 579.1K downloads during the last seven tracked days.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Qwen2.5-VL-3B-Instruct is a image text to text model published by Qwen. OpenModelStats has tracked the model since Sep 6, 2026, most recently observing it Oct 6, 2026.

Published
Jan 26, 2025
Last updated
Apr 6, 2025
Library
transformers
License
—
Task
Image Text to Text
Parameters
3,754,622,976
Spaces
—
Derivative models
36
Velocity 7D/day
82.7K
transformerssafetensorsqwen2_5_vlimage-text-to-textmultimodalconversationalenarxiv:2309.00071arxiv:2409.12191arxiv:2308.12966eval-resultstext-generation-inference

Model family

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

Similar models

Models similar to Qwen2.5-VL-3B-Instruct
ModelDL 30D
Qwen2.5-VL-3B-Instruct-AWQQwen303.3K
Nanonets-OCR2-3Bnanonets262.6K
Nanonets-OCR-snanonets67.7K
typhoon-ocr-3btyphoon-ai33.2K
churro-3Bstanford-oval23.6K
Qwen2.5-VL-3B-Instruct-abliteratedhuihui-ai22.6K
Qwen/Qwen2.5-VL-3B-Instruct — Downloads, Growth & Stats | OpenModelStats