HiVG-3B-Base
xingxm/HiVG-3B-Base
Tracked by OpenModelStats since September 30, 2026View on Hugging Face ↗
- Downloads 30DRolling recent-window download count as reported by the source platform.
- 435
- Total downloadsCumulative all-time download counter reported by the source platform.
- 1,995
- 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.
- 12
- Rank · tracked modelsPosition among all eligible models tracked by OpenModelStats, ordered by recent downloads. #214 among tracked Image to Text models.
- #43,939
- 120(down 120 places)this week
- Parameters
- 3.8B
- Last source update
- Apr 17, 2026
- It moved from #215 to #214 among tracked Image to Text models this week.
Downloads over time
Cumulative total downloads observed by OpenModelStatsLikes over time
Rank among tracked models
Lower is betterOverview
HiVG-3B-Base is a image to text model published by xingxm. OpenModelStats has tracked the model since Sep 30, 2026, most recently observing it Oct 5, 2026.
- Published
- Apr 14, 2026
- Last updated
- Apr 17, 2026
- Library
- transformers
- License
- mit
- Task
- Image to Text
- Parameters
- 3,756,720,128
- Spaces
- —
- Derivative models
- —
- Velocity 7D/day
- —
transformerssafetensorsqwen2_5_vlimage-text-to-textsvghivgvector-graphicstext-to-svgimage-to-svghierarchical-tokenizationautoregressive-generationcode-generation
Publisher
xingxmView publisher statistics →Similar models
| Model | DL 30D |
|---|---|
| sarashina2.2-vision-3bsbintuitions | 853 |
| Arabic-handwritten-OCR-4bit-Qwen2.5-VL-3B-v2sherif1313 | 9,890 |
| blip2-opt-2.7b-cocoSalesforce | 400 |
| sarashina2.2-ocrsbintuitions | 1,663 |
| llava-phi-3-mini-hfxtuner | 520 |
| Arabic-OCR-DeepSeek-OCR-2loay | 1,038 |