The Turkish-focused AI model that understands Turkish from the root — ranked first among open Turkish models on TurkishMMLU.
The 32-billion-parameter release is on Hugging Face with its measurement protocol and GGUF quantizations. Under the same protocol (TurkishMMLU clean-652, option rotation): Erk-14B 67.18%, Erk-32B 71.01%.
Open Turkish models — accuracy (%), identical conditions
Most AI models used for Turkish today were designed for English and adapted to Turkish afterward. Every Turkish user pays the price: the model doesn't understand Turkish's agglutinative structure, over-splits words, and runs slower and more expensively. We built Erk on a strong, open-source base model (Qwen3-14B) with an extensive Turkish training pipeline on top — continued pretraining and instruction tuning — with one goal: the model that understands Turkish best.
#1 among open Turkish models on TurkishMMLU (69.7% accuracy)
Efficient tokenization — half the tokens of GPT-4 for the same Turkish text
Grounded in real documents and authoritative sources; rejects false premises
Fully open source — downloadable, inspectable, extensible
Erk is a 14-billion-parameter, Turkish-focused large language model developed by eCloud Yazılım Teknolojileri. It is built on the open-source Qwen3-14B, with a Turkish development pipeline layered on top — extensive Turkish continued pretraining and instruction tuning grounded in real documents.
On the independent, public TurkishMMLU benchmark, Erk ranks first among the open Turkish models tested, at 69.7% accuracy. Its strongest subjects are geography, philosophy, religion & ethics, and history. Evaluation was reported transparently, under identical conditions for all compared models.
Erk-14B is open source and publicly available on Hugging Face. The full training recipe is open in the nanosohbet repository. The larger Erk-32B has since been released together with its measurement protocol and GGUF quantizations.
Erk is open source and downloadable on Hugging Face. Contact us for commercial use and partnerships.