Fact-checking and judgesText analysis

MiniCheck

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.

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

Developer
UT Austin and Bespoke Labs, USA
First release
Apr 2024
Latest release
Aug 2024
Sizes
0.4B – 7B
License
Commercial use with conditionsSmall versions (RoBERTa, DeBERTa, Flan-T5) — MIT; Bespoke-MiniCheck-7B — CC-BY-NC 4.0, commercial use by agreement
Russian
Not supported
Ready-made builds
GGUF
Running
Available in OllamaAlso runs without a GPU
Industries
Customer support, Documents and accounting, Legal
Deploy on your server Hugging Face GitHub

What it does

  • Checking RAG bot answers against documents
  • Finding unsupported claims in reports and summaries
  • Automated quality control of AI answers

Where it is used

Customer supportLegal and complianceCompany knowledge bases

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. Bespoke-MiniCheck-7B
  2. MiniCheck RoBERTa-Large, DeBERTa-v3-Large, Flan-T5-Large

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library
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 MiniCheck be used in a commercial project?

With conditions. License: Small versions (RoBERTa, DeBERTa, Flan-T5) — MIT; Bespoke-MiniCheck-7B — CC-BY-NC 4.0, commercial use by agreement. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does MiniCheck 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 MiniCheck support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download MiniCheck and what does it cost?

The MiniCheck 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.

DetailsModeration and safetyGranite GuardianIBM · USACommercial use allowed

IBM judge models: they catch harm, profanity and jailbreak attempts, and in RAG and agents check whether an answer is grounded in the documents. You can state your own rule in words.

Details

Source: huggingface.co/bespokelabs/Bespoke-MiniCheck-7B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.