Deepfake detectionText analysis

MAGE

A Longformer-based AI-text detector: it holds a long document whole and was trained on texts from many different language models. It errs in both directions; its output is a reason for a human to check.

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

Developer
UC Santa Barbara and co-authors, USA
First release
Jan 2024
Latest release
May 2024
Sizes
about 150M (Longformer-base)
License
Commercial use allowedApache 2.0
Russian
Not supported
Running
On your own serverAlso runs without a GPU
Industries
Education, Media and production, Science and research, Security
Deploy on your server Hugging Face

What it does

  • Checking long articles and reports as a whole
  • Filtering machine text in a publication flow
  • Comparing detectors on your own data
  • Fine-tuning for your own subject area

Where it is used

EducationMedia and newsroomsSciencePlatform moderation

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
no versions
ClusterServer with several GPUs — flagship versions
no versions

Versions

  1. Обновление карточки модели
  2. MAGE (веса на Hugging Face)

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 MAGE be used in a commercial project?

Yes. License: Apache 2.0. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does MAGE 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 MAGE support Russian?

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

Where can I download MAGE and what does it cost?

The MAGE 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

Deepfake detectionDesklib AI Text DetectorDesklib · IndiaCommercial use allowed

A recent open AI-text detector on DeBERTa-v3-large, trained on the RAID dataset, with a separate version for academic work. It errs in both directions - a human always reviews the result.

DetailsDeepfake detectionRADARIBM Research and The Chinese University of Hong Kong · USACommercial use with conditions

An AI-text detector trained together with a paraphraser: it was deliberately taught not to give up when the text has been rewritten. It errs in both directions; a human reviews the output.

DetailsDeepfake detectionHC3 ChatGPT DetectorHello-SimpleAI · ChinaCommercial use with conditions

One of the first open AI-text classifiers, trained on the HC3 corpus of paired human and ChatGPT answers. It errs in both directions: its output is a reason to talk to the author, not proof.

Details

Source: huggingface.co/yaful/MAGE. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.