sarashina2.2-vision-3b

sbintuitions/sarashina2.2-vision-3b

Image to Text3.8B parameterstransformersLicense: mitGated
Tracked by OpenModelStats since September 8, 2026View on Hugging Face ↗
Downloads 30D
853
Total downloads
19.9K
Gained 7D
0
0% vs baseline
Gained 30D
—
Likes
20
+0 in 7D
Rank · tracked models
#35,478
254(down 254 places)this week
Parameters
3.8B
Last source update
Aug 31, 2026
Momentum
4.4
  • It moved from #194 to #195 among tracked Image to Text models this week.

Downloads over time

Cumulative total downloads observed by OpenModelStats

Likes over time

Rank among tracked models

Lower is better

Overview

sarashina2.2-vision-3b is a image to text model published by sbintuitions. OpenModelStats has tracked the model since Sep 8, 2026, most recently observing it Aug 31, 2026.

Published
Nov 19, 2025
Last updated
Aug 31, 2026
Library
transformers
License
mit
Task
Image to Text
Parameters
3,801,475,696
Spaces
—
Derivative models
—
Velocity 7D/day
0
transformerssafetensorssarashina2_visiontext-generationmultimodalvision-languageimage-to-textcustom_codejaenarxiv:2404.07824arxiv:2403.19454

Publisher

sbintuitionsView publisher statistics →

Derived from sbintuitions/sarashina2.2-3b-instruct-v0.1 (reported by the source; parent not yet tracked).

Similar models

Models similar to sarashina2.2-vision-3b
ModelDL 30D
HiVG-3B-Basexingxm443
Arabic-handwritten-OCR-4bit-Qwen2.5-VL-3B-v2sherif131312.6K
blip2-opt-2.7b-cocoSalesforce397
sarashina2.2-ocrsbintuitions1,651
llava-phi-3-mini-hfxtuner528
Qwen3.5-4B-Base-ZitGen-V1lolzinventor1,483
sbintuitions/sarashina2.2-vision-3b — Downloads, Growth & Stats | OpenModelStats