Demo
Multimodal-OCR
Nanonets / olmOCR / RolmOCR / Aya-Vision / Qwen2-VL-OCR · running · License apache-2.0
- HF likes
- 418
- Status
- running
- License
- apache-2.0
- SDK
- gradio
Hugging Face
prithivMLmods/Multimodal-OCR
- SpaceprithivMLmods/Multimodal-OCR
- SDKgradio
- Likes418
- Licenseapache-2.0
- Updated2026-05-21T21:41:49.000Z
Technical tags
Try this demo
Decision details
Nanonets / olmOCR / RolmOCR / Aya-Vision / Qwen2-VL-OCR
- Availabilityrunning
- Last checked2026-09-28T22:18:55.388847+00:00
- Licenseapache-2.0
- Publisher (host)prithivMLmods
- Formatstext
- RequirementsNone detected
- Example inputPrompt / chat message
- Example outputGenerated text
Underlying models
6 · not the same as publisher
-
allenai/olmOCR-7B-0725 underlying model
-
kernels-community/flash-attn2 underlying model
-
nanonets/Nanonets-OCR2-3B underlying model
-
prithivMLmods/Qwen2-VL-OCR-2B-Instruct underlying model
-
reducto/RolmOCR underlying model
-
CohereLabs/aya-vision-8b underlying model