Text analysis

GLiNER

Finds the entities you need in text without training: just list what to look for (name, amount, date). GLiNER2 also classifies text. Multilingual versions understand Russian.

Developer
Urchade Zaratiana and Fastino AI, France / USA
First release
Feb 2024
Latest release
Aug 2026
Sizes
about 50M to 500M
License
Commercial use allowedApache 2.0
Russian
Not stated
Running
On your own serverAlso runs without a GPU
Industries
Documents and accounting, Software development, Legal
Deploy on your server Hugging Face GitHub

What it does

  • Extracting names, amounts and dates from emails and contracts
  • Parsing requests into CRM fields
  • Classifying requests by topic

Where it is used

Legal departmentsAccounting and document managementSales and CRM

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. GLiNER2.5 small, base, multi
  2. GLiNER2 multi
  3. GLiNER2
  4. GLiNER v2.1 (в том числе multi)
  5. GLiNER base и multi

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 GLiNER 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 GLiNER 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 GLiNER 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 GLiNER and what does it cost?

The GLiNER 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

Moderation and safetyGLiNER-PIIGLiNER community (Fastino, Knowledgator, NVIDIA and others) · USACommercial use allowed

Small GLiNER-based models for finding personal data: passports, phone numbers, accounts, addresses. Data types are set in words. Russian is not officially supported.

DetailsText analysisDeBERTa-v3 и mDeBERTa-v3Microsoft · USACommercial use allowed

A time-tested encoder behind many classifiers and NER models (including GLiNER). The multilingual mDeBERTa-v3 understands Russian.

DetailsText analysisruBERT, ruRoBERTa, ruELECTRA (ai-forever)SberDevices (ai-forever) · RussiaCommercial use allowed

Sber's Russian-language encoders trained on large Russian corpora. A base for classifiers, NER and semantic search in Russian.

Details

Source: huggingface.co/fastino/gliner2.5-multi-v1. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.