Translation

ALMA и X-ALMA

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

The last open version came out in Aug 2024. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
Johns Hopkins University and Microsoft, USA
First release
Sep 2023
Latest release
Aug 2024
Sizes
7B – 13B
License
Commercial use with conditionsMIT on the model card, but the models are built on Llama 2, so the Llama 2 terms also apply
Russian
Supported
Running
On your own serverNeeds a GPU
Industries
Documents and accounting, Science and research
Deploy on your server Hugging Face GitHub

What it does

  • Translation between English and Russian
  • Experiments with LLM-based translation
  • Base for fine-tuning a translator

Where it is used

Research groupsTranslation agencies (pilots)

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. X-ALMA, 50 языков
  2. ALMA-R (улучшенное обучение)
  3. ALMA 7B и 13B

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 ALMA и X-ALMA be used in a commercial project?

With conditions. License: MIT on the model card, but the models are built on Llama 2, so the Llama 2 terms also apply. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does ALMA и X-ALMA 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 ALMA и X-ALMA support Russian?

Yes, Russian is listed on the model card.

Where can I download ALMA и X-ALMA and what does it cost?

The ALMA и X-ALMA 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

TranslationTowerUnbabel · PortugalNon-commercial only

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

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.

DetailsTextEuroLLMUTTER consortium (Unbabel, universities of Lisbon, Edinburgh, Amsterdam and others) · European UnionCommercial use allowed

European language models trained on all EU languages and several others, with a focus on translation. Russian is supported. Permissive license.

Details

Source: huggingface.co/haoranxu/X-ALMA-13B-Group1. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.