Drawings and CADImage + textDocuments and OCR

MatCha и DePlot

Small models that turn an image of a chart or diagram into a table of numbers and answer questions about it. Values read off an image are approximate, so the result has to be checked.

The last open version came out in Jul 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 Research, USA
First release
Apr 2023
Latest release
Jul 2023
Sizes
282M
License
Commercial use allowedApache 2.0
Russian
Not stated
Running
On your own serverAlso runs without a GPU
Industries
Documents and accounting, Finance, Media and production, Science and research
Deploy on your server Hugging Face

What it does

  • Turning a chart from a report or PDF into a table
  • Natural-language questions about a diagram
  • A short text description of a chart
  • Digitising diagrams from old documents

Where it is used

Document workflows and reportingFinancial analysisMedia and content preparationResearch

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
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Обновление карточек и весов
  2. MatCha PlotQA и chart2text
  3. DePlot — график в таблицу
  4. MatCha base и MatCha ChartQA

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 MatCha и DePlot 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 MatCha и DePlot 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 MatCha и DePlot support Russian?

The model card does not list languages, so Russian support cannot be promised — it has to be tested on your own examples.

Where can I download MatCha и DePlot and what does it cost?

The MatCha и DePlot 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

Drawings and CADQZhou-Flowchart-VLKingsoft · ChinaCommercial use allowed

It reads a flowchart from an image and first writes out its structure as JSON - blocks, links and branching conditions - and only then answers a question about the chart. The parse still has to be checked against the original.

DetailsDocuments and OCRSmolDocling и Granite-DoclingIBM and Hugging Face · USACommercial use allowed

Tiny models for the open Docling document converter: they turn a page into markup with tables, formulas and code. Run on an ordinary laptop.

DetailsDocuments and OCRNougatMeta · USACommercial use with conditions

An early model that converts scientific PDFs into text with formulas. Now outdated and outperformed by almost all modern OCR models.

Details

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