anemll5d ago

iPhone 17 Pro Demonstrated Running a 400B LLM

https://twitter.com/anemll/status/2035901335984611412

Anemll (@anemll) on X

Running 400B model on iPhone! 0.6 t/s Credit @danveloper @alexintosh @danpacary @anemll

X (formerly Twitter)
Show threadcj00
It’s 400B but it’s mixture of experts so how many are active at any time?
Mar 23 at 3:08pmWeb
Show threadsimonw5d ago
Looks like it's Qwen3.5-397B-A17B so 17B active. https://github.com/Anemll/flash-moe/tree/iOS-App
GitHub - Anemll/flash-moe at iOS-App

Contribute to Anemll/flash-moe development by creating an account on GitHub.

GitHub