Skip to content
Local AI Wizard
Your machine
Theme

surya-ocr-2

Datalab · datalab-to/surya-ocr-2

Weights license: Publisher terms: OpenRAIL-M (modified, Datalab) · code and components may use other terms

Reported by the publisher1 resultDatalab's model card · read 2026-10-25 · not ranked · see them
Memory needed~1 GBQ4 weights + working room, before the machine's reserve
Parameters0.7 BHub safetensors total
Repository updated2026-05-27A commit is not a release date

Quality

No comparable score

We track no public, comparable benchmark that covers this model yet. No score is inferred.

Reported by the publisher

1 result · Datalab's model card · read 2026-10-25
Score
83.3

Values as printed on the card, with the publisher's own settings (card section: Benchmarks › olmOCR-bench); column “Surya OCR 2 (Datalab)”. Not comparable across publishers and not used in any ranking. Model card

Runs on

Fast memory holds it 119

The planning estimate fits the memory the model can use quickly: graphics card VRAM, or unified memory within the macOS GPU share.

Show all 119

Hardware profiles grouped by the Q4 planning estimate on each machine (dedicated GPUs reserve 2 GB; unified and system memory 25%, 2 to 8 GB): the fast memory holds it, it is within memory but outside the fast part (layers offloaded to PC RAM, or above the macOS GPU share), or the machine is one memory tier short. Not a measured fit or speed.

Consider it for

Datalab released surya-ocr-2 on 2026-05-27: a vision-language model that answers about images, with 686M parameters on the Hugging Face count and the Publisher terms: OpenRAIL-M (modified, Datalab) license.

Check first

License: commercial use unanswered (this license has not been reviewed for commercial use yet). At Q4 the weights load about 0.5 GB before each machine's reserve; image resolution, video frames and context add memory, and the vision encoder needs support in the runtime you pick.

Measured speed

No published measurement for this checkpoint

Tokens per second are shown only when a source publishes them with hardware, build and setup. They are never estimated.

How to run

Runtime compatibility and tokens per second have not been measured for this entry. Published metadata and a memory estimate do not prove a successful local run.

Library in source: transformers

Documented ways to run it

Copied as printed in the linked source (read 2026-10-18); not run by this site.

Setup stated first by the source · Surya OCR
pip install surya-ocr
Surya OCR · model card · From python
from PIL import Image
from surya.inference import SuryaInferenceManager
from surya.recognition import RecognitionPredictor

manager = SuryaInferenceManager()
recognition_predictor = RecognitionPredictor(manager)

# Default: full-page OCR. One VLM call per page; returns layout + content as
# HTML <div data-bbox=... data-label=...> blocks.
predictions = recognition_predictor([Image.open(IMAGE_PATH)])

# Block mode: pre-run layout, then per-block OCR. Auto-selected when
# `layout_results` is passed.
from surya.layout import LayoutPredictor
layout = LayoutPredictor(manager)
layouts = layout([Image.open(IMAGE_PATH)])
predictions = recognition_predictor([Image.open(IMAGE_PATH)], layouts)
Setup stated first by the source · Surya OCR
pip install surya-ocr
Surya OCR · model card · OCR (text recognition)
surya_ocr DATA_PATH

Choose my computer

Technical details

What the source and the catalog store for this checkpoint. Missing fields are left out, never zero.

Checkpoint / source
datalab-to/surya-ocr-2
Task
image-text-to-text
Architecture
Qwen3_5ForConditionalGeneration
Library in source
transformers
Weight license
Publisher terms: OpenRAIL-M (modified, Datalab)datalab-to/surya-ocr-2 LICENSE: AI Pubs Open RAIL-M License (Modified) (Hugging Face) · read 2026-10-19source
Commercial use
This license has not been reviewed for commercial use yet
Released
Announcing Surya OCR 2: small, accurate, multilingual | Datalab (publisher announcement; meta article:published_time) · read 2026-10-19source
Every stored field12 fields
Revision checked
3b3d4cdf88d6928b0acdc75181b13206ea67c4a3
Architecture
Qwen3_5ForConditionalGeneration
Library
transformers
Hub task tag
image-text-to-text
Formats
transformers, safetensors
Access
Open download
Publisher kind
Official
Hub parameter count
686,154,304safetensors.total
Repository created
2026-05-14creation is not the model's release
Repository updated
2026-05-27a commit is not a release date
Hub downloads (30 days) · likes
1,374,182 · 138this repository only · read 2026-10-25
Catalog state
Hub config or weights found; no inventory benchmark link

Sources

Identity and published specifications come from the checkpoint page. Benchmark scores belong to the named release and do not measure speed on your computer.

Curated facts checked: 2026-10-19. The license and release date cite the publisher's sources; parameters, files and task come from the Hugging Face record, and memory is a labelled estimate from its parameter count. A value no source states stays empty; a repository commit is not a model release date.