Tabular dataText

TableLlama

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

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

Developer
OSU NLP Group, Ohio State University, USA
First release
Nov 2023
Latest release
Nov 2023
Sizes
7B
License
Commercial use with conditionsCC-BY 4.0 on the model card; the Llama 2 base model has its own license
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Documents and accounting, Finance, Science and research
Deploy on your server Hugging Face GitHub

What it does

  • Answering questions about tables inside documents
  • Matching columns across different tables
  • Finding and completing records in reference books

Where it is used

Document workflowAnalytics and reportingResearch groups

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. TableLlama-7B

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 TableLlama be used in a commercial project?

With conditions. License: CC-BY 4.0 on the model card; the Llama 2 base model has its own license. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does TableLlama need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller 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 TableLlama support Russian?

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

Where can I download TableLlama and what does it cost?

The TableLlama 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 dataTableGPT2 / TableGPT-R1Zhejiang University · ChinaCommercial use allowed

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

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/osunlp/TableLlama. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.