PepperOCR-VL
sionic-ai/PepperOCR-VL
Tracked by OpenModelStats since October 4, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 84
- Total downloadsCumulative all-time download counter reported by the source platform.
- 84
- 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.
- 6
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads.
- —
- –this week
- Parameters
- 4.5B
- Last source update
- Oct 4, 2026
Downloads over time
Daily gain between consecutive observationsLikes over time
Rank among tracked models
Lower is betterNot enough tracked history yet for a chart.
OpenModelStats began tracking this model on 2026-10-04. Charts appear as daily observations accumulate.
Overview
PepperOCR-VL is a image text to text model published by sionic-ai. OpenModelStats has tracked the model since Oct 4, 2026, most recently observing it 2h ago.
- Published
- Oct 4, 2026
- Last updated
- Oct 4, 2026
- Library
- transformers
- License
- agpl-3.0
- Task
- Image Text to Text
- Parameters
- 4,539,265,536
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- —
transformerssafetensorsqwen3_5image-text-to-textocrdocument-parsingdocument-understandingmarkdownlatextable-recognitionmultilingualvllm
Publisher
sionic-aiView publisher statistics →Derived from Qwen/Qwen3.5-4B (reported by the source; parent not yet tracked).
Similar models
| Model | DL 30D |
|---|---|
| Qwen3.5-4B-MLX-4bitlmstudio-community | 9,610 |
| Huihui-Qwen3.5-4B-abliteratedhuihui-ai | 8,472 |
| Qwen-Drive-1.0-4BQwen | 5,903 |
| Qwen3.5-4B-Baseunsloth | 5,445 |
| Qwen3.5-4B-MLX-8bitlmstudio-community | 4,912 |
| Qwen3.5-4B-Unredacted-MAXprithivMLmods | 3,499 |