From Data to Device: ELMOD An Efficient German-First 2.7B Language Model for Mobile Inference

-->

Computer Science > Computation and Language

arXiv:2607.24585v1 (cs)

[Submitted on 27 Jul 2026]

Title: From Data to Device: ELMOD An Efficient German-First 2.7B Language Model for Mobile Inference

Authors: Darina Gold , Alexander Schwirjow , Viktor Haag , Viktor Hangya , Joel Schlotthauer , Fabian Küch , Luzian Hahn

View a PDF of the paper titled From Data to Device: ELMOD An Efficient German-First 2.7B Language Model for Mobile Inference, by Darina Gold and 6 other authors

View PDF

Abstract: We present ELMOD - Efficient Language Model for On-Device Deployment - a compact (2.7B) German language model designed for efficient inference on resource-constrained hardware. ELMOD was trained on a limited computational budget (55k H100 GPU hours) using exclusively publicly available data. We developed a suite of German-specific data pre-processing, which differ from English-oriented counterparts in their handling of morphological variation, compounding, and orthographic conventions. Furthermore, we introduced a quality filtering and rephrasing step, which increased the instructional quality of the data, improved performance during the annealing phase, and reduced overall compute requirements. Thanks to our architectural model and data choices, including prefiltering, our educational-quality filtering and rephrasal to raise the educational-quality, ELMOD is the strongest perfo

…