TranslationText

Tower

Language models tailored for translation and multilingual text work: translating, editing, and assessing translation quality. Russian is supported. Non-commercial license.

Developer
Unbabel, Portugal
First release
Jan 2024
Latest release
Jun 2025
Sizes
2B – 72B
License
Non-commercial onlyCC-BY-NC 4.0 and CC-BY-NC-SA 4.0: non-commercial use only
Russian
Supported
Ready-made builds
GGUF
Running
On your own serverAlso runs without a GPU
Industries
Documents and accounting, Marketing and content, Customer support
Deploy on your server Hugging Face

What it does

  • Translation that respects context and terminology
  • Post-editing machine translation
  • Assessing the quality of a finished translation

Where it is used

Translation agencies (for research and pilots)Research groups

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
fits

Versions

  1. Tower+ 2B, 9B, 72B
  2. TowerInstruct Mistral 7B v0.2
  3. TowerInstruct 13B
  4. TowerBase и TowerInstruct 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. Quantization compresses a model so it takes less video memory and runs on more modest hardware. Answers change slightly, so quality is checked on your own examples.

Frequently asked questions

Can Tower be used in a commercial project?

No. License: CC-BY-NC 4.0 and CC-BY-NC-SA 4.0: non-commercial use only. A commercial product needs a different model or a separate agreement with the rights holder.

What hardware does Tower 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 Tower support Russian?

Yes, Russian is listed on the model card.

Where can I download Tower and what does it cost?

The Tower 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

TranslationHunyuan-MT / Hy-MTTencent · ChinaCommercial use with conditions

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.

DetailsTranslationSeed-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.

DetailsTranslationALMA и X-ALMAJohns Hopkins University and Microsoft · USACommercial use with conditions

Research translators based on Llama 2. The first ALMA covered 5 pairs with English, including Russian; X-ALMA expanded coverage to 50 languages.

Details

Source: huggingface.co/Unbabel/Tower-Plus-72B. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.