titleMobile AI Factory: Building Specialized Language Models for Your Mobile Device
authorsEvan Li, Krishna Deshpande, Wen Cheng, Shyamnath Gollakota
date2026-11-10
venuearXiv (preprint, not peer reviewed)
idarXiv:2611.13509
affiliationUniversity of Washington
upvotes19 (Hugging Face Daily Papers, 2026-11-18)
linksabs pdf hf code
cite
relatedReflex: Visually Grounded Reactive Humanoid Control
Agentic Abstention: Do Agents Know When to Stop Instead of Act?
Infrathon: Benchmarking Language Agents for Real-World, Long-Horizon AI Infra Optimization
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models
Thinking While Speaking: Inference-Time Knowledge Transfer for Responsive and Intelligent Conversational Voice Agents
abstractSmall language models (SLMs) running on mobile devices can keep user data private and work without connectivity. But they perform well only when fine-tuned for the target task and sized for the target device, a process that today requires repeated expert tuning. We present {\it Mobile AI Factory}, an agentic system that builds a fine-tuned, quantized SLM for a given task and phone. Given a task specification and a target phone, an orchestrator LLM chooses whether to tune hyperparameters, mine real data, or generate synthetic examples, while fixed rules roll back changes that hurt accuracy. The factory searches from small to large models across base models and quantizations, adapts its accuracy goal as it searches, and uses real measurements of the target phone across inference engines and backends. We evaluate Mobile AI Factory on ten tasks and four Android phones. On an unseen testset, its on-device models outperform two five-shot frontier models on five tasks, by up to 0.34, and match them on three more. Its search comes within 0.03 of exhaustively training all 27 model variants on an entity extraction task, while using 19times less GPU time. Phone measurements also matter: the best configuration changes across phones. Without phone measurements, Claude Opus 5.5, given the full hardware and model specifications, misses the app's requirements in 25\% of easy and moderate cases and in 60\% of hard ones. Code is available at: https://github.com/evanly-gh/SLM_Factory.

bibtex

@misc{li2026mobile,
  title={Mobile AI Factory: Building Specialized Language Models for Your Mobile Device},
  author={Evan Li and Krishna Deshpande and Wen Cheng and Shyamnath Gollakota},
  year={2026},
  eprint={2611.13509},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2611.13509}
}