# surya-ocr-2.5

> We also ship smaller models for line-level text detection and ocr error detection. It works on a range of documents (see usage and benchmarks).

- **Organisation:** datalab-to
- **Category:** OCR & Document AI, Vision-Language Models
- **Parameters:** 689M
- **Context length:** 262,144 tokens
- **Licence:** OpenRAIL (Commercial use with conditions)
- **Released:** 2026-10-25
- **Hugging Face:** 144.4K downloads (30 days), 54 likes

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q4_K_M | 0.97 |
| Q8_0 | 1.32 |
| F16 | 2.04 |

## Runs with

- [llama.cpp](https://selfhost.directory/project/llamacpp)
- [LM Studio](https://lmstudio.ai)
- [SGLang](https://selfhost.directory/project/sglang)
- [Transformers](https://github.com/huggingface/transformers)
- [vLLM](https://selfhost.directory/project/vllm)
- [Jan](https://jan.ai) (community)
- [KoboldCpp](https://selfhost.directory/project/koboldcpp) (community)
- [LocalAI](https://selfhost.directory/project/localai) (community)
- [Ollama](https://selfhost.directory/project/ollama) (community)

## About

We also ship smaller models for line-level text detection and ocr error detection. It works on a range of documents (see usage and benchmarks).

Our managed platform runs both Surya, and variants of our highest accuracy model, Chandra.

Get started with $5 in free credits — sign up (takes under 30 seconds) or try our free public playground.

Surya is named for the Hindu sun god, who has universal vision.

Each row links to four annotated views of the same page: text-line detection, OCR, layout and reading order (Surya 2.5).

The example pages are public pages from OmniParseBench. The newspaper (The Alpha, 1881), reference book and math paper are from olmOCR-bench (Ai2, ODC-BY 1.0). The government form is a US federal form (public domain). The handwritten letter is from the Library of Congress, Manuscript Division, Carrie Chapman Catt Papers (public domain). The corporate page is from ParseBench (Apache 2.0). The Japanese form is made from a form of the National Tax Agency, Japan, under the Public Data License 1.0: 「国税庁の様式」（国税庁）（https://www.nta.go.jp/）を加工して作成. The OCR column renders Surya 2.5's HTML output; layout and reading order are drawn from its blocks, and the detection image is from the text-line detector.

## Alternatives

- [datalab-to/surya-ocr-2](https://selfhost.directory/models/datalab-to/surya-ocr-2) (686M, OpenRAIL, ≈2.03 GB): It works on a range of documents (see usage and benchmarks).
- [ATH-MaaS/OvisOCR3](https://selfhost.directory/models/ath-maas/ovisocr3) (853M, Apache 2.0, ≈2.41 GB): OvisOCR3 is a unified 0.8B multimodal model for OCR and document understanding. It integrates document parsing, general OCR, key information extraction, document figure captioning, and cross-page table reconstruction into a single compact model.
- [lightonai/LightOnOCR-2-1B](https://selfhost.directory/models/lightonai/lightonocr-2-1b) (1B, Apache 2.0, ≈2.75 GB): Best OCR model . LightOnOCR-2-1B is LightOn's flagship OCR model, refined with RLVR training for maximum accuracy. We recommend this variant for most OCR tasks.
- [lightonai/LightOnOCR-3-0.8B](https://selfhost.directory/models/lightonai/lightonocr-3-0.8b) (853M, Apache 2.0, ≈2.41 GB): Smallest model. LightOnOCR-3-0.8B is the lightest model of LightOn's LightOnOCR-3 family, with the same layout and visual understanding features.
- [ATH-MaaS/OvisOCR2](https://selfhost.directory/models/ath-maas/ovisocr2) (853M, Apache 2.0, ≈2.41 GB): We are pleased to announce the release of OvisOCR2, a compact 0.8B end-to-end model for page-level document parsing. Given a document page image, OvisOCR2 generates a Markdown representation in natural reading order, covering text, formulas, tables, and visual regions.
- [PaddlePaddle/PaddleOCR-VL-1.6](https://selfhost.directory/models/paddlepaddle/paddleocr-vl-1.6) (959M, Apache 2.0, ≈2.64 GB): PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training

More: https://selfhost.directory/models/datalab-to/surya-ocr-2.5/alternatives

## Runs well on

- [GeForce RTX 4060](https://selfhost.directory/models/datalab-to/surya-ocr-2.5/on/rtx-4060): F16
- [Apple M4 (16 GB)](https://selfhost.directory/models/datalab-to/surya-ocr-2.5/on/apple-m4-16gb): F16
- [Radeon RX 6700 XT](https://selfhost.directory/models/datalab-to/surya-ocr-2.5/on/rx-6700-xt): F16
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/datalab-to/surya-ocr-2.5/on/rtx-3060): F16
- [Arc B580](https://selfhost.directory/models/datalab-to/surya-ocr-2.5/on/arc-b580): F16
- [Tesla T4](https://selfhost.directory/models/datalab-to/surya-ocr-2.5/on/tesla-t4): F16

## Similar size

- [stepfun-ai/GOT-OCR2_0](https://selfhost.directory/models/stepfun-ai/got-ocr2_0) (716M)
- [lightonai/LightOnOCR-3-0.8B](https://selfhost.directory/models/lightonai/lightonocr-3-0.8b) (853M)
- [ATH-MaaS/OvisOCR3](https://selfhost.directory/models/ath-maas/ovisocr3) (853M)
- [microsoft/Florence-2-large](https://selfhost.directory/models/microsoft/florence-2-large) (777M)
- [microsoft/Florence-2-large-ft](https://selfhost.directory/models/microsoft/florence-2-large-ft) (770M)
- [datalab-to/surya-ocr-2](https://selfhost.directory/models/datalab-to/surya-ocr-2) (686M)

## FAQ

**How much VRAM does surya-ocr-2.5 need?**
About 2.0 GB at FP16 / BF16.

**Can surya-ocr-2.5 run on the RTX 4060?**
Yes. It fits at FP16 / BF16 (about 2.0 GB). It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.

**Can I use surya-ocr-2.5 commercially?**
Yes, with conditions. It is released under OpenRAIL. Commercial use allowed, but with use-based restrictions that pass on to derivatives.

**How do I run surya-ocr-2.5 with Ollama or llama.cpp?**
With Ollama: ollama run hf.co/datalab-to/surya-ocr-2.5-gguf:Q8_0. With llama.cpp: llama-server -hf datalab-to/surya-ocr-2.5-gguf:Q8_0, which starts an OpenAI-compatible server.

## Links

- huggingface: https://huggingface.co/datalab-to/surya-ocr-2.5
- github: https://github.com/datalab-to/surya%7D%7D
- paper: https://arxiv.org/abs/2105.15203
- demo: https://www.datalab.to/playground?utm_source=gh-surya

---
Source: https://selfhost.directory/models/datalab-to/surya-ocr-2.5