Computer-use agentsMath and reasoningImage + text

AREX-2

An agent model of 27B (based on Qwen3.8-27B) for long tasks: it proposes a solution, measures the result, analyzes errors and revises the solution over several rounds. A 262K-token context. Stated as a research model.

Developer
Beijing Academy of Artificial Intelligence (BAAI), China
First release
Sep 2026
Latest release
Sep 2026
Sizes
27B
License
Commercial use allowedApache 2.0; the terms of the Qwen base model must also be followed
Russian
Not stated
Running
On your own serverNeeds a GPU
Industries
Science and research, Software development, Education
Deploy on your server Hugging Face GitHub

What it does

  • iterative improvement of code and algorithms
  • machine learning tasks with a verifiable result
  • deep search and gathering information on a topic

Where it is used

software development and ITresearch groupsR&D departments

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
no versions

Versions

  1. AREX-2 27B
  2. AREX-Turbo 4B

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 AREX-2 be used in a commercial project?

Yes. License: Apache 2.0; the terms of the Qwen base model must also be followed. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does AREX-2 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 AREX-2 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 AREX-2 and what does it cost?

The AREX-2 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

TextQwenAlibaba · ChinaCommercial use with conditions

A family of language models with strong Russian language support, from small versions for a laptop to a flagship on par with commercial APIs.

DetailsTextKimiMoonshot AI · ChinaCommercial use with conditions

Very large Moonshot MoE models for agentic work. K3 (2.8 trillion parameters) was the largest open model at release, with up to 1M tokens of context and image understanding; K2.7-Code is built for programming.

DetailsTextDeepSeekDeepSeek · ChinaCommercial use allowed

DeepSeek's flagship line: from the first 7B/67B to V4-Pro with 1.6 trillion parameters. Closed-model quality under an open MIT license; V4-Flash-Vision-Exp and V4.1-Flash understand images, context up to 1M tokens.

Details

Source: huggingface.co/BAAI/AREX-2. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.