GlotMAX-17-8B

Model Sources

• Paper: LLaMAX2: Your Translation-Enhanced Model Also Performs Well in Reasoning
• Link: https://arxiv.org/pdf/2510.09189
• Repository: https://github.com/CONE-MT/LLaMAX2.0

Model Description

Qwen3-XPlus series models start from Qwen3 instruct models with layer-slective tuning using small amount of parallel data alone.

Meanwhile, comprehensive testing on 16 reasoning tasks, such as bbeh, Livecodebench, Olymmath and so on, shows that it surpasses existing translation-enhanced models and performs on par with Qwen3 instruct models.

🔥 Excellent Translation Performance

Qwen3-XPlus significantly boost translation performance in both high- and low-resource languages.

🔥 Excellent Reasoning Performance

Trained Data Covered Languages

• en (English)
• ar (Arabic)
• bn (Bengali)
• cs (Czech)
• de (German)
• es (Spanish)
• fr (French)
• hu (Hungarian)
• ja (Japanese)
• ko (Korean)
• ru (Russian)
• sr (Serbian)
• sw (Swahili)
• te (Telugu)
• th (Thai)
• vi (Vietnamese)
• zh (Chinese)

Model Index

We implement multiple versions of the Qwen3-XPlus model, the model links are as follows:

Citation

If our model helps your work, please cite this paper:

@misc{gaoLLaMAX2YourTranslationEnhanced2025,
  title = {{{LLaMAX2}}: {{Your Translation-Enhanced Model}} Also {{Performs Well}} in {{Reasoning}}},
  shorttitle = {{{LLaMAX2}}},
  author = {Gao, Changjiang and Huang, Zixian and Gong, Jingyang and Huang, Shujian and Li, Lei and Yuan, Fei},
  year = {2025},
  month = oct,
  number = {arXiv:2510.09189},
  eprint = {2510.09189},
  primaryclass = {cs},
  publisher = {arXiv},
  doi = {10.48550/arXiv.2510.09189},
  archiveprefix = {arXiv}
}

---