Translation

M2M-100

An early Meta translator that translates directly between 100 languages, without English in the middle. Russian is supported. Old, but light and permissively licensed.

The last open version came out in Mar 2021. The family has not been updated for a long time: the model still works, but do not expect fixes or new sizes.

Developer
Meta, USA
First release
Oct 2020
Latest release
Mar 2021
Sizes
418M – 12B
License
Commercial use allowedMIT
Russian
Supported
Ready-made builds
GGUF
Running
On your own serverAlso runs without a GPU
Industries
Documents and accounting, Customer support
Deploy on your server Hugging Face GitHub

What it does

  • Translation between any pair of 100 languages
  • Quick draft translation on modest hardware
  • Base for fine-tuning to your subject area

Where it is used

Logistics and foreign tradeCustomer 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. M2M-100 418M и 1.2B на Hugging Face
  2. M2M-100 (публикация и веса в fairseq)

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 M2M-100 be used in a commercial project?

Yes. License: MIT. It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does M2M-100 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 M2M-100 support Russian?

Yes, Russian is listed on the model card.

Where can I download M2M-100 and what does it cost?

The M2M-100 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

TranslationNLLB-200Meta · USANon-commercial only

A translator for 200 languages, including rare and minor ones. Russian is supported. Strong language coverage, but the license prohibits commercial use.

DetailsTranslationMADLAD-400Google · USACommercial use allowed

Google's translator for more than 400 languages under a permissive license. Russian is supported. A good substitute for NLLB when commercial use is needed.

DetailsTranslationOPUS-MT (MarianMT)Helsinki-NLP, University of Helsinki · FinlandCommercial use allowed

More than a thousand small translators, each for its own language pair. Russian-English and back are available. Fast even on a regular CPU.

Details

Source: huggingface.co/facebook/m2m100_418M. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.