BigMoeOnEdge
Run AI models far bigger than your phone's memory
This comes straight from BigMoeOnEdge’s own GitHub page — it’s free. Need help installing? →
About this app
BigMoeOnEdge uses a clever trick to run very large AI models on an ordinary phone by keeping only the parts it needs in memory at a time — no quality shortcuts and no special hardware.
It is a project for the curious: slow but genuinely impressive, and everything stays on the device.
From the app’s home page
- See the codeHow it’s made — every line is public
- Questions & commentsTalk with the people who make it
- Report a problemTell the makers something is broken
- All versionsOlder downloads and what changed
- LicenseThe rules for using and sharing it
More like this
All Tools →
OGAM
Offline AI that chats, sees, speaks and draws
Local LLMs
Chat with an AI model with no internet at all
OlliteRT
Turn your phone into a private AI server
Servllama
One tap turns your phone into an AI server