Image + textDocuments and OCR

Pix2Struct

Reads a document or a screenshot as an image and answers with structure: text, fields, answers to questions. In HR it is fine-tuned for resumes and forms. A human makes the decision about a candidate; automatic screening without review must not be used.

The last open version came out in Mar 2023. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
Google, USA
First release
Mar 2023
Latest release
Mar 2023
Sizes
282M – 1.3B
License
Commercial use allowedApache 2.0
Russian
Not supported
Running
On your own serverAlso runs without a GPU
Industries
Documents and accounting, HR, Finance
Deploy on your server Hugging Face GitHub

What it does

  • Extracting data from resumes and forms supplied as images
  • Questions about the content of a scan
  • Parsing tables and diagrams in documents

Where it is used

HR and recruitingDocument workflowsAnalytics

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. pix2struct-chartqa и ai2d, графики и схемы
  2. pix2struct-docvqa, вопросы к документу
  3. pix2struct-base и pix2struct-large

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can Pix2Struct be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does Pix2Struct need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Some versions also run on an ordinary CPU, without a GPU. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does Pix2Struct support Russian?

No. The developer documentation lists the supported languages and Russian is not among them.

Where can I download Pix2Struct and what does it cost?

The Pix2Struct weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

Documents and OCRDonutNAVER CLOVA · South KoreaCommercial use allowed

Reads a scanned document and returns a filled-in field structure straight away, with no separate OCR step. In HR it is fine-tuned for parsing resumes and forms. A human makes the decision about a candidate; automatic screening without review must not be used.

DetailsDocuments and OCRUDOPMicrosoft · USACommercial use allowed

One model for every document task: reading, answering questions about a page, extracting fields, classification. In HR it is used to parse resumes and attached scans. A human makes the decision about a candidate; automatic screening without review must not be used.

DetailsText analysisNuExtractNuMind · FranceCommercial use allowed

Models for template-based data extraction: give it a document or scan and a JSON field template, get a filled-in JSON back. NuExtract3 (4B) also converts scans to Markdown.

Details

Source: huggingface.co/google/pix2struct-base. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.