OvisOCR3
ATH-MaaS/OvisOCR3
Tracked by OpenModelStats since October 21, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 2,954
- Total downloadsCumulative all-time download counter reported by the source platform.
- 2,954
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- —
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 100
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #2168 among tracked Image Text to Text models.
- #20,905
- 7316(up 7316 places)this week
- Parameters
- 853M
- Last source update
- Oct 27, 2026
- It moved from #2559 to #2168 among tracked Image Text to Text models this week.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
OvisOCR3 is a image text to text model published by ATH-MaaS. OpenModelStats has tracked the model since Oct 21, 2026, most recently observing it 15h ago.
- Published
- Oct 21, 2026
- Last updated
- Oct 27, 2026
- Library
- transformers
- License
- apache-2.0
- Task
- Image Text to Text
- Parameters
- 852,985,920
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- —
transformerssafetensorsqwen3_5image-text-to-textocrdocument-parsingmultimodalmarkdowntablesformulaskey-information-extractionfigure-captioning
Publisher
ATH-MaaSView publisher statistics →Derived from Qwen/Qwen3.5-0.8B (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| OvisOCR2ATH-MaaS | 107.8K |
| Qwen3.5-0.8B-4bitmlx-community | 9,774 |
| LightOnOCR-3-0.8Blightonai | 9,408 |
| Qwen3.5-0.8B-8bitmlx-community | 6,730 |
| Qwen3.5-0.8B-Baseunsloth | 5,106 |
| Intern-Decision-0.8Binternlm | 3,808 |