Qianfan-OCR

baidu/Qianfan-OCR

Image Text to Text4.7B parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since August 24, 2026View on Hugging Face ↗
Downloads 30D
247.3K
Total downloads
1.6M
Gained 7D
+14.9K(increase)
1.0%(up) vs baseline
Gained 30D
—
Likes
1,204
+1 in 7D
Rank · tracked models
#1,346
4(up 4 places)this week
Parameters
4.7B
Last source update
Apr 29, 2026
Momentum
82.2
  • Qianfan-OCR gained 14.9K downloads during the last seven tracked days.
  • It moved from #213 to #214 among tracked Image Text to Text models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

Qianfan-OCR is a image text to text model published by baidu. OpenModelStats has tracked the model since Aug 24, 2026, most recently observing it Oct 3, 2026.

Published
Mar 18, 2026
Last updated
Apr 29, 2026
Library
transformers
License
apache-2.0
Task
Image Text to Text
Parameters
4,741,408,256
Spaces
—
Derivative models
—
Velocity 7D/day
2,135
transformerssafetensorsqianfan_ocrimage-text-to-textvision-languageocrdocument-intelligenceqianfanconversationalmultilingualarxiv:2603.13398arxiv:2509.18189

Similar models

Models similar to Qianfan-OCR
ModelDL 30D
QianfanOCRbairongz1,066
LLaVA-OneVision-1.5-4B-Instructlmms-lab1,005
Mage-VLmicrosoft10.9K
Mage-VL-8bitmlx-community245
Qwen3.5-4B-AWQ-BF16-INT8cyankiwi380
Qwen3.5-4B-AWQ-BF16-INT4cyankiwi284
baidu/Qianfan-OCR — Downloads, Growth & Stats | OpenModelStats