Press center
Zubr: ZuBrIQ models go open — our build on top of open source
On July 13 ArtCloud published the Zubr family on Hugging Face — ZuBrIQ platform models built and adapted by the team from open source models: the quantized flagship Zubr1.0-35B-A3B (AWQ, 131,072-token context) and the Zubr1.0-VL-4B vision model. They run in Russian, Belarusian and English inside the Republic of Belarus via an OpenAI-compatible API.
On July 13, 2026, the ArtCloud team published the Zubr model family on Hugging Face — language models of the ZuBrIQ platform that run inside the Republic of Belarus.
What stands behind the name: Zubr is ArtCloud's own build — quantization and a production-ready build for inference, configuration for serving in Belarus, the platform-side integration, and testing on Russian- and Belarusian-language tasks. By publishing the models openly, we give back to the community what we ourselves received from open source.
The first release included two models:
- Zubr1.0-35B-A3B-AWQ — the flagship. A MoE model (35B parameters, ~3B active per token) in AWQ quantization (~24 GB of weights) with a context of 131,072 tokens — ready for inference on vLLM, including tool calling.
- Zubr1.0-VL-4B — a vision model: understands images, scans and screenshots; powers multimodal requests and the Vision Bridge (screen understanding) in ZuBrIQ.
Legal, local, OpenAI-compatible
The main point of the release is legal clarity. Both models are distributed under the Apache 2.0 license and run on infrastructure in Belarus: no request leaves the country, billing is in Belarusian rubles. The flagship is served through an OpenAI-compatible API at `api.zubriq.by` (alias `zubr`): existing code built on the OpenAI SDK switches to Zubr by changing a single line of configuration.
For companies this is a practical alternative to the "either foreign cloud AI or nothing" choice: chat, document work, tool calling and multimodality — legal, without leaving the country.
An open ecosystem
The models and weights are published on Hugging Face — download them, run them on your own hardware, or adapt them to your task. Our builds are open: companies can inspect what is inside and assemble their own solution on this foundation.
The family keeps growing: after the July release, ArtCloud trained and published Zubr1.5-VL-32B — the first fine-tuned model of the family. It is built around a QLoRA adapter trained on the legislation of the Republic of Belarus (28 codes and their application practice); the model understands document scans and handles legal scenarios.
The Zubr models are part of the ZuBrIQ platform, running since August 2025: LLM chat, document work, assistants and BYN billing at zubriq.by.