OvisOCR2

ATH-MaaS/OvisOCR2

Image Text to Text853M parameterstransformersLicense: apache-2.0
Tracked by OpenModelStats since September 2, 2026View on Hugging Face ↗
Downloads 30D
225.9K
Total downloads
448.1K
Gained 7D
+112.6K(increase)
44.8%(up) vs baseline
Gained 30D
—
Likes
479
+8 in 7D
Rank · tracked models
#1,409
15(up 15 places)this week
Parameters
853M
Last source update
Aug 28, 2026
Momentum
98.6
  • OvisOCR2 gained 112.6K downloads during the last seven tracked days.
  • It moved from #226 to #228 among tracked Image Text to Text models this week.

Downloads over time

Rolling recent-window downloads as reported

Likes over time

Rank among tracked models

Lower is better

Overview

OvisOCR2 is a image text to text model published by ATH-MaaS. OpenModelStats has tracked the model since Sep 2, 2026, most recently observing it Oct 2, 2026.

Published
Jul 13, 2026
Last updated
Aug 28, 2026
Library
transformers
License
apache-2.0
Task
Image Text to Text
Parameters
852,985,920
Spaces
—
Derivative models
3
Velocity 7D/day
16.1K
transformerssafetensorsqwen3_5image-text-to-textocrdocument-parsingmultimodalmarkdowntablesformulasvllmconversational

Model family

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

Similar models

Models similar to OvisOCR2
ModelDL 30D
Qwen3.5-0.8B-Baseunsloth6,063
Qwen3.5-0.8B-8bitmlx-community5,147
Qwen3.5-0.8B-4bitmlx-community5,095
Qwen3.5-0.8B-MLX-8bitlmstudio-community3,321
Qwen3.5-0.8B-MLX-4bitlmstudio-community2,705
WARD-0.8btricao11051,947
ATH-MaaS/OvisOCR2 — Downloads, Growth & Stats | OpenModelStats