Translated open-sources Lara Mini Base: 0.6B-active MoE beats models trained on 4-6x more tokens

NielsRogge · x · 2026-11-16

Translation company Translated released Lara Mini Base, an open-weights model built around the thesis that language diversity is a resource, not a trade-off. The paper notes non-English data makes up at most 12% of pretraining in the open models they reviewed.

Key facts:

The authors find the MoE architecture reduces capacity competition between languages — multilingual training can help rather than dilute small models.

Original post →

More from Models

Models channel →