We’ve trained a study model called “Efficient Language Model for On-Device Deployment” (ELMOD-2.7B), to establish the foundation for future on-device language model applications. Built on a first-of-its-kind German dataset and an end-to-end pipeline we developed from scratch, the model has 2.7B parameters and was trained on 3.8T tokens across a mix of German, English, and code. While it’s not yet a fully optimized, deployment-ready system, it lays important groundwork for future work and industry-relevant models.
This video shows the model running directly on a smartphone chip. Mobile- or Edge LLMs are still in their infancy, but they promise lower latency, improved privacy, offline capability and improved performance for specialized use cases.
The demo highlights a simple persona setting to showcase how the model can be adapted to different roles on resource-constrained hardware. It’s an early prototype and not a fully matured model, but it demonstrates what’s possible as mobile LLM inference rapidly evolves.
We will share more details about the training setup, conversion pipeline, and performance in upcoming articles about our research project(s).
Author: Alexander Schwirjow, Valentina Ciardini and Joel Schlotthauer from Fraunhofer IIS
*The audio overlay was generated using Allinga TTS by Fraunhofer IIS
Header image c
