ニュース
From Data to Device: ELMOD An Efficient German-First 2.7B Language Model for Mobile Inference
arXiv cs.AI · 公開日 · 読了3分
30秒で要点
- 何が起きたか
- ELMOD is a 2.7 billion parameter German language model optimized for mobile devices, matching 7B model performance on German tasks.
- なぜ重要か
- Matters for engineers building German-language applications on phones or edge devices with limited computational resources and memory.
- 注意点
- Paper focuses on German language specifically; results may not transfer to other languages or multilingual scenarios requiring different preprocessing.
この要約を音声で聴く
記事より
-->
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
原文からの抜粋です。全文は配信元でお読みください。
- language model
- inference
The Agent Architect
1つのパターン、1つのトレードオフ、1つの本番障害事例。エージェントシステムを構築する人のための短い週刊ブリーフィング。
週1回のメール、ワンクリックで購読解除できます。アドレスはブリーフィングの送信のみに使用します。