What are the hardware requirements for Surya Ocr 2?

Surya Ocr 2 requires approximately 1.4 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Surya Ocr 2 and how large is it?

Surya Ocr 2 is developed by datalab-to, a model with 686.2m parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Surya Ocr 2?

Surya Ocr 2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Surya Ocr 2 by datalab-to — VRAM 1.4GB

Name: Surya Ocr 2
Author: datalab-to

Surya Ocr 2 is an open-source language model by datalab-to. Features: 686.2m LLM, VRAM: 1.4GB, License: openrail, LLM Explorer Score: 0.39.

Arxiv:2105.15203 Conversational Endpoints compatible Eval-results Image-text-to-text Layout Markdown Ocr Pdf Qwen3 5 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/datalab-to/surya-ocr-2

Surya Ocr 2 Parameters and Internals

LLM Name	Surya Ocr 2
Repository 🤗	https://huggingface.co/datalab-to/surya-ocr-2
Model Size	686.2m
Required VRAM	1.4 GB
Updated	2026-08-09
Maintainer	datalab-to
Model Type	qwen3_5
Model Files	1.4 GB
Model Architecture	Qwen3_5ForConditionalGeneration
License	openrail
Transformers Version	5.2.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>

Rank the Surya Ocr 2 capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation