Open large language models (LLMs) have demonstrated improving multilingual capabilities in recent years. In this paper, we present a study of open LLMs for multilingual machine translation (MT) across a range of languages, and investigate the effects of model scaling and data scaling when adapting open LLMs to multilingual MT through continual pretraining and instruction finetuning. Based on the Gemma3 model family, we develop MiLMMT-46, which achieves top-tier multilingual translation performance across 46 languages. Extensive experiments show that MiLMMT-46 consistently outperforms recent state-of-the-art (SOTA) models, including Seed-X, HY-MT-1.5, and TranslateGemma, and achieves competitive performance with strong proprietary systems such as Google Translate and Gemini 3 Pro.

翻译：近年来，开放大语言模型（LLMs）在多语言能力方面持续展现出进步。本文针对一系列语言，研究了开放大语言模型在多语言机器翻译（MT）中的应用，并通过持续预训练和指令微调，探讨了将开放大语言模型适配于多语言机器翻译任务时，模型扩展与数据扩展所产生的影响。基于Gemma3模型家族，我们开发了MiLMMT-46，该模型在46种语言上实现了顶尖的多语言翻译性能。大量实验表明，MiLMMT-46在性能上持续超越近期最先进的模型，包括Seed-X、HY-MT-1.5和TranslateGemma，并与Google Translate、Gemini 3 Pro等强大的专有系统取得了具有竞争力的性能。