How to run Gemopus-4-E4B-it on iPhone? Recommended backend / inference stack?

#1
by thucdangvan020999 - opened

I’m really interested in deploying Gemopus-4-E4B-it locally on an iPhone (especially leveraging Apple Silicon + on-device inference).

What is the recommended backend for iOS?

  • MLX (Apple)
  • llama.cpp (Metal)
  • MLC-LLM
  • LiteRT-LM
  • Other options?

Sign up or log in to comment