Tiny Aya: Bridging Scale and Multilingual Depth

TL;DR

Tiny Aya is a small, efficient multilingual language model with 3.35B parameters that achieves state-of-the-art translation and understanding across 70 languages through region-aware training and specialization.

Contribution

It introduces a scalable, efficient approach to multilingual modeling with region-specific models and a comprehensive evaluation framework, advancing practical deployment.

Findings

State-of-the-art translation quality across 70 languages

Effective multilingual understanding and generation

Region-specialized models improve performance in targeted languages

Abstract

Tiny Aya redefines what a small multilingual language model can achieve. Trained on 70 languages and refined through region-aware posttraining, it delivers state-of-the-art in translation quality, strong multilingual understanding, and high-quality target-language generation, all with just 3.35B parameters. The release includes a pretrained foundation model, a globally balanced instruction-tuned variant, and three region-specialized models targeting languages from Africa, South Asia, Europe, Asia-Pacific, and West Asia. This report details the training strategy, data composition, and comprehensive evaluation framework behind Tiny Aya, and presents an alternative scaling path for multilingual AI: one centered on efficiency, balanced performance across languages, and practical deployment.