Qari-OCR-v0.3-VL-2B-Instruct

NAMAA-Space/Qari-OCR-v0.3-VL-2B-Instruct

Image Text to Text2.2B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since September 4, 2026View on Hugging Face ↗
Downloads 30D
2,831
Total downloads
304.3K
Gained 7D
+910(increase)
0.3%(up) vs baseline
Gained 30D
—
Likes
22
+4 in 7D
Rank · tracked models
#16,616
191(up 191 places)this week
Parameters
2.2B
Last source update
Jun 10, 2025
Momentum
72.3
  • Qari-OCR-v0.3-VL-2B-Instruct gained 910 downloads during the last seven tracked days.
  • It moved from #1719 to #1710 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

Qari-OCR-v0.3-VL-2B-Instruct is a image text to text model published by NAMAA-Space. OpenModelStats has tracked the model since Sep 4, 2026, most recently observing it Oct 4, 2026.

Published
Apr 10, 2025
Last updated
Jun 10, 2025
Library
transformers
License
apache-2.0
Task
Image Text to Text
Parameters
2,208,985,600
Spaces
—
Derivative models
—
Velocity 7D/day
130
transformerssafetensorsqwen2_vlimage-text-to-textimage-to-textconversationalardataset:NAMAA-Space/QariOCR-v0.3-markdown-mixed-datasetarxiv:2506.02295license:apache-2.0text-generation-inferenceendpoints_compatible

Similar models

Models similar to Qari-OCR-v0.3-VL-2B-Instruct
ModelDL 30D
Qwen2-VL-2B-InstructQwen1.4M
NuExtract-2.0-2Bnumind87.5K
Qwen2-VL-2B-Instruct-4bitmlx-community15.6K
Qwen2-VL-2BQwen4,677
Qwen2-VL-2B-Instructunsloth1,338
Qwen2-VL-OCR-2B-InstructprithivMLmods1,069
NAMAA-Space/Qari-OCR-v0.3-VL-2B-Instruct — Downloads, Growth & Stats | OpenModelStats