Translation

Hunyuan-MT / Hy-MT

Tencent translators for 33 languages; the first version won the WMT25 competition. Russian is supported. The small 1.8B version runs on a laptop; the new Hy-MT2 is under Apache 2.0.

Developer
Tencent, China
First release
Aug 2025
Latest release
May 2026
Sizes
1.8B – 30B-A3B
License
Commercial use with conditionsHy-MT2: Apache 2.0; earlier Hunyuan-MT and HY-MT1.5: Tencent license (does not apply in the EU, UK and South Korea)
Russian
Supported
Running
On your own serverAlso runs without a GPU
Industries
Documents and accounting, Customer support, Retail and marketplaces
Deploy on your server Hugging Face GitHub

What it does

  • Translating documents while keeping formatting
  • Translation with a set glossary of terms
  • Translating correspondence with Chinese partners

Where it is used

Trade with China and importsLogisticsCustomer support

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. Hy-MT2 1.8B, 7B, 30B-A3B
  2. HY-MT1.5 1.8B и 7B
  3. Hunyuan-MT-7B и Hunyuan-MT-Chimera-7B

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 Hunyuan-MT / Hy-MT be used in a commercial project?

With conditions. License: Hy-MT2: Apache 2.0; earlier Hunyuan-MT and HY-MT1.5: Tencent license (does not apply in the EU, UK and South Korea). Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Hunyuan-MT / Hy-MT 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 Hunyuan-MT / Hy-MT support Russian?

Yes, Russian is listed on the model card.

Where can I download Hunyuan-MT / Hy-MT and what does it cost?

The Hunyuan-MT / Hy-MT 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

TranslationSeed-XByteDance Seed · ChinaCommercial use allowed

A compact ByteDance translator for 28 languages, close in quality to large closed systems. Russian is supported. Ready-made compressed versions are available.

DetailsTranslationTranslateGemmaGoogle · USACommercial use with conditions

Translators based on Gemma 3 for 55 languages that can also translate text in images. Russian is supported. The 4B version fits on a laptop.

DetailsTextHunyuan / HyTencent · ChinaCommercial use with conditions

Tencent language models: from small 0.5B–7B to Hy4-preview with 770 billion parameters. Since 2026 the line has been renamed Hy, and new versions are released under Apache 2.0.

Details

Source: huggingface.co/tencent/Hy-MT2-30B-A3B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.