What are the hardware requirements for Surya Ocr 2 Gguf?

Surya Ocr 2 Gguf requires approximately 0.2 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Surya Ocr 2 Gguf and how large is it?

Surya Ocr 2 Gguf is developed by datalab-to. 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 Gguf?

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

Surya Ocr 2 Gguf by datalab-to — VRAM 0.2GB

Name: Surya Ocr 2 Gguf
Author: datalab-to

Surya Ocr 2 Gguf is an open-source language model by datalab-to. Features: LLM, VRAM: 0.2GB, License: openrail, Quantized, LLM Explorer Score: 0.35.

Arxiv:2105.15203 Conversational Endpoints compatible Gguf Image-text-to-text Layout Markdown Ocr Pdf Quantized Qwen3 5 Region:us

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

Surya Ocr 2 Gguf Parameters and Internals

LLM Name	Surya Ocr 2 Gguf
Repository 🤗	https://huggingface.co/datalab-to/surya-ocr-2-gguf
Required VRAM	0.2 GB
Updated	2026-08-09
Maintainer	datalab-to
Model Type	qwen3_5
Model Files	0.2 GB 1.3 GB
GGUF Quantization	Yes
Quantization Type	gguf
Model Architecture	Qwen3_5ForConditionalGeneration
License	openrail
Transformers Version	5.2.0
Tokenizer Class	TokenizersBackend
Padding Token	<\|endoftext\|>

Rank the Surya Ocr 2 Gguf 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

Best Alternatives to Surya Ocr 2 Gguf

Best Alternatives	Context / RAM	Downloads	Likes
Agent Sft Harness R1.imatrix	0K / 6.5 GB	45	1