jina-vlm

jinaai/jina-vlm

Image Text to Text2.5B parameterstransformersLicense: cc-by-nc-4.0
Tracked by OpenModelStats since September 6, 2026View on Hugging Face ↗
Downloads 30D
427
Total downloads
15.8K
Gained 7D
+76(increase)
0.5%(up) vs baseline
Gained 30D
—
Likes
124
+0 in 7D
Rank · tracked models
#44,056
187(down 187 places)this week
Parameters
2.5B
Last source update
Apr 2, 2026
Momentum
30.1
  • jina-vlm gained 76 downloads during the last seven tracked days.
  • It moved from #4169 to #4193 among tracked Image Text to Text models this week.

Downloads over time

Daily gain between consecutive observations

Likes over time

Rank among tracked models

Lower is better

Overview

jina-vlm is a image text to text model published by jinaai. OpenModelStats has tracked the model since Sep 6, 2026, most recently observing it Oct 6, 2026.

Published
Nov 17, 2025
Last updated
Apr 2, 2026
Library
transformers
License
cc-by-nc-4.0
Task
Image Text to Text
Parameters
2,481,403,760
Spaces
—
Derivative models
—
Velocity 7D/day
11
transformerssafetensorsjvlmtext-generationmultimodalmultilingualvlmvision-languageqwen3siglip2image-text-to-textconversational

Publisher

jinaaiView publisher statistics →

Derived from Qwen/Qwen3-1.7B-Base (reported by the source; parent not yet tracked).

Similar models

jinaai/jina-vlm — Downloads, Growth & Stats | OpenModelStats