
Ai2 Releases OLMoE iOS App for On-Device AI Testing
Ai2 has announced the release of an open-source iOS app for its OLMoE language model, allowing users to test the model on their devices. The app is available for download from the Apple App Store and requires an iPhone 15 Pro or newer, or any M-series iPad.
OLMoE is part of Ai2's commitment to open-source language models, providing researchers and developers with tools to experiment with on-device AI. The app enables users to experience state-of-the-art models for real-world tasks, research efficient local AI models, and integrate OLMoE into other iOS applications.
The OLMoE model has been optimized for on-device use with Q4_K_M quantization, maintaining performance while reducing size. The app was developed in collaboration with GenUI, utilizing Swift bindings for Llama.cpp to achieve an average processing speed of 41 tokens per second on an iPhone 16 Pro.
The source code for the Ai2 OLMoE app is fully open, allowing researchers and developers to adopt and adapt the model for further AI advancements. This release marks a significant step in the evolution of on-device AI functionality as mobile processing capabilities continue to grow.
We hope you enjoyed this article.
Consider subscribing to one of several newsletters we publish. For example, in the Daily AI Brief you can read the most up to date AI news round-up 6 days per week.
Also, consider following us on social media:
Subscribe to Daily AI Brief
Daily report covering major AI developments and industry news, with both top stories and complete market updates
Whitepaper
Stanford HAI’s 2025 AI Index Reveals Record Growth in AI Capabilities, Investment, and Regulation
The 2025 AI Index by Stanford HAI provides a comprehensive overview of the global state of artificial intelligence, highlighting significant advancements in AI capabilities, investment, and regulation. The report details improvements in AI performance, increased adoption in various sectors, and the growing global optimism towards AI, despite ongoing challenges in reasoning and trust. It serves as a critical resource for policymakers, researchers, and industry leaders to understand AI's rapid evolution and its implications.
Read more