Can your smartphone become your personal AI workstation?
We're building LOMI (Local Model Intelligence) — an Android application that brings local AI inference to smartphones using compatible GGUF language models and llama.cpp.
Cloud AI is convenient, but it also comes with dependencies on internet connectivity, remote infrastructure and external services.
We believe smartphones should be capable of doing more AI processing locally.
With LOMI, we're exploring how far we can push on-device AI, making it easier for people to download, manage and interact with language models directly on Android.
We'd love to hear from the local AI community:
Do you currently run LLMs locally on your Android device?
Which models do you find most practical for mobile devices?
What matters most to you: inference speed, model quality, memory usage or battery efficiency?
What is the biggest limitation preventing you from using local AI regularly?
We're building LOMI and want community feedback to influence what comes next.
Website: https://lomi.ra-studio.dev/
What would you want from a serious local AI application for Android?


p/runevr
p/producthunt
p/google-cloud-platform
p/operum
p/murror
p/tabstack
p/dino-kids
p/any-video-to-text
p/seldon
p/rithub
p/jot-2-0
p/okapi-2
p/gatrends
p/appxiom
p/flamigo
p/dots-7
p/kodlo
p/replay-11
Replies
Be the first to reply
Have a question or a thought to share? Add a comment above to start the conversation.