Yandex Releases Open Language Model Alice AI Foundation LLM
Yandex has developed from scratch a large language model Alice AI Foundation LLM and has opened its weights for commercial and research use. This was reported by the company's representatives.
The architecture of the model has 80 billion parameters, with about 3 billion of them being used simultaneously. The volume of training data was 18 trillion tokens. The company clarified that the training was carried out without the use of foreign third-party components, characterizing the development as fully sovereign, according to "Vedomosti" citing a Yandex representative.
Developers have released the tuned parameters of the model, which allows third-party specialists to launch it on their own infrastructure and conduct further training. The license does not limit the application of the model in commercial or research projects.
Yandex plans to use Alice AI Foundation LLM as a technological foundation for a future model with elements of reasoning and for expanding the agent functions of the "Alisa AI" assistant. Experts note that the current version is a basic architecture, not a finished product for end-users.
What it means
Developers can freely download the open parameters of Alice AI Foundation LLM, launch the model, and further train it for commercial and scientific tasks.
Sources
- iXBT.com: Яндекс с нуля создал языковую модель на 80 млрд параметров media outlet
- Hi-Tech Mail: «Яндекс» разработал ИИ-модель без иностранных составляющих media outlet
This article was prepared with the help of AI and translated from the Russian original. Spotted an error — let us know.
Published 21 September 2026, 12:16 · No updates · Russian original