Tabular dataText

TableGPT2 / TableGPT-R1

A family for working with tables and databases: it understands data structure, writes parsing code and answers questions about exports.

Developer
Zhejiang University, China
First release
Nov 2024
Latest release
Dec 2025
Sizes
7B – 72B
License
Commercial use allowedApache 2.0
Russian
Not supported
Ready-made builds
GGUF
Running
On your own serverNeeds a GPU
Industries
Finance, Retail and marketplaces, Manufacturing and logistics, Software development
Deploy on your server Hugging Face GitHub

What it does

  • Answering questions about tables and data exports
  • Automated data analysis with generated code
  • A helper for BI and internal reporting

Where it is used

Analytics and reportingFinance departmentsManufacturing and warehousing

Hardware requirements

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

Versions

  1. TableGPT-R1 на базе Qwen3-8B
  2. TableGPT2-7B (заявлена также версия 72B)

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. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can TableGPT2 / TableGPT-R1 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 TableGPT2 / TableGPT-R1 need?

At minimum: One GPU with 16–80 GB — mid-size versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does TableGPT2 / TableGPT-R1 support Russian?

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

Where can I download TableGPT2 / TableGPT-R1 and what does it cost?

The TableGPT2 / TableGPT-R1 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

Tabular dataTableLLMRUCKBReasoning, Renmin University of China · ChinaCommercial use with conditions

A model for office work with tables: for a given question it returns either a direct answer or code to process the data in a table or document.

DetailsTabular dataTableLlamaOSU NLP Group, Ohio State University · USACommercial use with conditions

A general-purpose model for tables: filling gaps, finding rows, matching columns and answering questions about the data.

DetailsTabular dataTabFMGoogle Research · USANon-commercial only

Google's large tabular model: classification and regression from examples without training, with numeric and categorical columns. Weights are for non-commercial use only.

Details

Source: huggingface.co/tablegpt/TableGPT-R1. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.