Arabic-handwritten-OCR-4bit-Qwen2.5-VL-3B-v2
sherif1313/Arabic-handwritten-OCR-4bit-Qwen2.5-VL-3B-v2
Tracked by OpenModelStats since September 5, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 8,446
- Total downloadsCumulative all-time download counter reported by the source platform.
- 122.1K
- Gained 7DIncrease in cumulative total downloads between OpenModelStats' own observations seven days apart.
- +24(increase)
- 0.0%(up) vs baseline
- Gained 30DIncrease in cumulative total downloads between OpenModelStats' own observations roughly thirty days apart.
- —
- LikesCommunity likes reported by the source platform.
- 12
- +0 in 7D
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #63 among tracked Image to Text models.
- #9,060
- 793(up 793 places)this week
- Parameters
- 3.9B
- Last source update
- Dec 29, 2025
- MomentumOpenModelStats' composite rising-model signal (0–100): a percentile blend of absolute 7-day download gains, capped percentage growth, and likes gained. See Methodology.
- 21.0
- Arabic-handwritten-OCR-4bit-Qwen2.5-VL-3B-v2 gained 24 downloads during the last seven tracked days.
- It moved from #69 to #63 among tracked Image to Text models this week.
Downloads over time
Daily gain between consecutive observationsLikes over time
Rank among tracked models
Lower is betterOverview
Arabic-handwritten-OCR-4bit-Qwen2.5-VL-3B-v2 is a image to text model published by sherif1313. OpenModelStats has tracked the model since Sep 5, 2026, most recently observing it Oct 5, 2026.
- Published
- Nov 10, 2025
- Last updated
- Dec 29, 2025
- Library
- —
- License
- apache-2.0
- Task
- Image to Text
- Parameters
- 3,862,624,760
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- 3
safetensorsqwen2_5_vlimage-to-textardataset:saleh-c4/arabic-ocr-imagesdataset:aamijar/muharaf-publicdataset:johnlockejrr/RASAMdataset:johnlockejrr/KHATT_v1.0_datasetbase_model:Qwen/Qwen2.5-VL-3B-Instructbase_model:quantized:Qwen/Qwen2.5-VL-3B-Instructlicense:apache-2.04-bit
Model family
Based on base-model relationships reported by the source's metadata.
Base model
Sibling models
- Nanonets-OCR2-3B249.5K
- Qwen2.5-VL-3B-Instruct-AWQ245.4K
- Nanonets-OCR-s85.6K
- typhoon-ocr-3b59.2K
- Qwen2.5-VL-3B-Instruct-GGUF16.7K
- PixelCraft-3B1,936
- colnomic-embed-multimodal-3b1,295
- ShotVL-3B1,095
Similar models
| Model | DL 30D |
|---|---|
| blip2-opt-2.7b-cocoSalesforce | 422 |
| sarashina2.2-ocrsbintuitions | 1,680 |
| sarashina2.2-vision-3bsbintuitions | 853 |
| HiVG-3B-Basexingxm | 431 |
| llava-phi-3-mini-hfxtuner | 516 |
| Qwen3.5-4B-Base-ZitGen-V1lolzinventor | 1,614 |