DuckDB-NSQL
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.
The last open version came out in Jan 2024. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.
- Developer
- MotherDuck and Numbers Station, USA
- First release
- Jan 2024
- Latest release
- Jan 2024
- Sizes
- 7B
- License
- Commercial use with conditionsLlama 2 Community License
- Russian
- Not stated
- Ready-made builds
- GGUF
- Running
- Available in OllamaNeeds a GPU
- Industries
- Software development, Finance
What it does
- Plain-language questions about CSV and Parquet exports
- DuckDB queries inside analytics scripts
- Quick analytics on a laptop without a server
Where it is used
Hardware requirements
Versions
- DuckDB-NSQL-7B v0.1
How to run it
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 DuckDB-NSQL be used in a commercial project?
With conditions. License: Llama 2 Community License. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.
What hardware does DuckDB-NSQL 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 DuckDB-NSQL 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 DuckDB-NSQL and what does it cost?
The DuckDB-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.
Similar models
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.
DetailsText to SQLXiYanSQL-QwenCoderAlibaba · ChinaCommercial use allowedAlibaba models for turning questions into SQL, based on Qwen2.5-Coder. They work with different SQL dialects; a small 3B version suits modest hardware.
DetailsCodeCode LlamaMeta · USACommercial use with conditionsA version of Llama 2 further trained on code, with variants for Python and for chat. Outdated, but many ready-made fine-tuned versions and tools exist.
DetailsSource: huggingface.co/motherduckdb/DuckDB-NSQL-7B-v0.1. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.


