TextImage + text

Aya

Multilingual models from Cohere's research arm, covering 23 to 100+ languages. Tiny Aya (2026, 3.3B) runs on a regular PC, but for non-commercial use only.

Developer: Cohere Labs, Canada
First release: Feb 2024
Latest release: Sep 2026
Sizes: 3.3B – 35B
License: Commercial use with conditionsAya 101: Apache 2.0; Aya 23, Expanse, Vision and Tiny Aya: CC-BY-NC, non-commercial only
Russian: Supported
Ready-made builds: GGUF
Running: Available in OllamaAlso runs without a GPU
Industries: Education, Customer support, Marketing and content

Deploy on your server Hugging Face

What it does

Translation and correspondence in less common languages
Multilingual chat assistant
Analysis of images with text (Vision)

Where it is used

EducationNon-profit projectsResearch

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

Sep 2026Tiny Aya Thinker
Feb 2026Tiny Aya
Mar 2025Aya Vision
Oct 2024Aya Expanse
May 2024Aya 23
Feb 2024Aya 101

How to run it

With Ollama — the fastest wayInstall Ollama on your computer or server and find the model in its library by name. Good enough to try the model on your own tasks in one evening.Find it in the Ollama library

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 Aya be used in a commercial project?

With conditions. License: Aya 101: Apache 2.0; Aya 23, Expanse, Vision and Tiny Aya: CC-BY-NC, non-commercial only. Restrictions vary — region, company revenue, attribution requirements. Have a lawyer check the terms before a commercial launch.

What hardware does Aya 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 Aya support Russian?

Yes, Russian is listed on the model card.

Where can I download Aya and what does it cost?

The Aya 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

SelectionI pick the model size for your task and hardware and test it on your examples.
DeploymentI deploy it on your server or in a closed network and provide an API.
Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Business models: document search with source citations, tool calling, many languages. Command A+ (2026) was the first under Apache 2.0, followed by the North line: code, translation and compact vision.

Details TextApertusSwiss AI (ETH Zurich, EPFL, CSCS) · SwitzerlandCommercial use allowed

Switzerland's public open model: weights, data and recipe are open, with more than 1000 languages in training. Version 1.5 understands images.

Details TextSarvamSarvam AI · IndiaCommercial use allowed

Indian models focused on 22 languages of India. Sarvam 30B and 105B (2026) are MoE models with strong reasoning and agent skills.

Details

Source: huggingface.co/CohereLabs/tiny-aya-global. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.