Fact-checking and judges

Patronus Lynx

Checks whether a chatbot invented a fact that is not in the source documents. The license is non-commercial. The checking model itself makes mistakes and does not replace manual review on important tasks.

The last open version came out in Jul 2024. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
Patronus AI, USA
First release
Jul 2024
Latest release
Jul 2024
Sizes
8B and 70B
License
Non-commercial onlyCC-BY-NC 4.0 — non-commercial use only
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Software development, Customer support, Documents and accounting, Finance
Deploy on your server Hugging Face

What it does

  • Finding invented facts in AI assistant answers
  • Checking that answers rest on the attached documents
  • Filtering out answers before they go to a customer

Where it is used

IT and software developmentCustomer supportDocument management

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. Llama-3-Patronus-Lynx-8B-Instruct и 70B-Instruct

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 Patronus Lynx be used in a commercial project?

No. License: CC-BY-NC 4.0 — non-commercial use only. A commercial product needs a different model or a separate agreement with the rights holder.

What hardware does Patronus Lynx 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 Patronus Lynx support Russian?

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

Where can I download Patronus Lynx and what does it cost?

The Patronus Lynx 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

Fact-checking and judgesHHEM (Vectara)Vectara · USACommercial use allowed

A small model that checks whether an AI answer is grounded in the source text or made up. Runs on a CPU and works well as a filter in RAG systems.

DetailsFact-checking and judgesMiniCheckUT Austin and Bespoke Labs · USACommercial use with conditions

Checks whether each claim in an AI answer is supported by the source documents. The small versions are free; the larger 7B is in Ollama but non-commercial.

DetailsFact-checking and judgesGLIDER (Patronus)Patronus AI · USANon-commercial only

A small judge: it scores against your criteria and highlights which part of the answer led to that score. The license is non-commercial. The judge itself makes mistakes and does not replace manual review.

Details

Source: huggingface.co/PatronusAI/Llama-3-Patronus-Lynx-70B-Instruct. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.