Text to SQLCode

NSQL

Name: NSQL
Author: Numbers Station

One of the first open text-to-SQL lines, including very small versions from 350M that run on an ordinary PC.

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: Numbers Station, USA
First release: Jul 2023
Latest release: Jul 2023
Sizes: 350M – 7B
License: Commercial use with conditionsmixed: the CodeGen-based versions are BSD-3-Clause, the Llama 2-based version uses the Llama 2 license
Russian: Not supported
Ready-made builds: GGUF
Running: On your own serverAlso runs without a GPU
Industries: Finance, Retail and marketplaces, Software development

Deploy on your server Hugging Face GitHub

What it does

Turning a question into SQL from a table description
Hints while writing queries
A local analyst helper with no data leaving the company

Where it is used

Analytics and reportingFinance departmentsDevelopment

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

Jul 2023NSQL-Llama-2-7B
Jul 2023NSQL 350M, 2B и 6B (на базе CodeGen)

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 NSQL be used in a commercial project?

With conditions. License: mixed: the CodeGen-based versions are BSD-3-Clause, the Llama 2-based version uses the Llama 2 license. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does NSQL 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 NSQL support Russian?

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

Where can I download NSQL and what does it cost?

The NSQL 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

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

A model for turning questions into SQL, built for the embedded analytics database DuckDB. Available in Ollama, convenient for working with CSV and Parquet locally.

Details Text to SQLSQLCoderDefog · USACommercial use with conditions

One of the first open models that turn a plain-language question into an SQL query against a database. Available in Ollama, but newer competitors are already stronger.

Details Text to SQLCodeSRUCKBReasoning, Renmin University of China · ChinaCommercial use allowed

An early line of open text-to-SQL models starting at 1B, including variants fine-tuned for specific database schemas.

Details

Source: huggingface.co/NumbersStation/nsql-llama-2-7B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.