What are the hardware requirements for GOT OCR 2.0 Hf?

GOT OCR 2.0 Hf requires approximately 1.1 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed GOT OCR 2.0 Hf and how large is it?

GOT OCR 2.0 Hf is developed by stepfun-ai, a model with 560.5m 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 GOT OCR 2.0 Hf?

GOT OCR 2.0 Hf is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GOT OCR 2.0 Hf by stepfun-ai — VRAM 1.1GB

Name: GOT OCR 2.0 Hf
Author: stepfun-ai

GOT OCR 2.0 Hf is an open-source language model by stepfun-ai. Features: 560.5m LLM, VRAM: 1.1GB, License: apache-2.0, LLM Explorer Score: 0.24.

Arxiv:2312.06109 Arxiv:2405.14295 Arxiv:2409.01704 Endpoints compatible Got Got ocr2 Image-text-to-text Multilingual Ocr2.0 Region:us Safetensors Vision Vision-language

Model Card on HF 🤗: https://huggingface.co/stepfun-ai/GOT-OCR-2.0-hf

GOT OCR 2.0 Hf Parameters and Internals

LLM Name	GOT OCR 2.0 Hf
Repository 🤗	https://huggingface.co/stepfun-ai/GOT-OCR-2.0-hf
Model Size	560.5m
Required VRAM	1.1 GB
Updated	2026-08-08
Maintainer	stepfun-ai
Model Type	got_ocr2
Model Files	1.1 GB
Model Architecture	GotOcr2ForConditionalGeneration
License	apache-2.0
Model Max Length	8000
Transformers Version	4.49.0.dev0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|endoftext\|>
Torch Data Type	bfloat16

Rank the GOT OCR 2.0 Hf 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