Skip to content

Android inference: add Phi-4-mini-reasoning on LiteRT-LM #583

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Daisuke Majima (MLBoy) (john-rocky) wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Android inference: add Phi-4-mini-reasoning on LiteRT-LM #583

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 4 additions & 0 deletions md/01.Introduction/03/Android_Inference.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,4 +39,8 @@ If you want to use `.gguf` files in the cloud and on edge devices simultaneously
2. Download the APK file (148MB) and install it on your device.
3. Launch the MLC Chat app. You'll see a list of AI models, including Phi-3-mini.

### Run Phi-4-mini-reasoning with LiteRT-LM

[Phi-4-mini-reasoning](https://huggingface.co/litert-community/Phi-4-mini-reasoning) is available as a community-converted int4 `.litertlm` bundle for Google's [LiteRT-LM](https://github.com/google-ai-edge/LiteRT-LM) on-device runtime. On Android it runs on CPU or GPU through the [Google AI Edge Gallery](https://github.com/google-ai-edge/gallery) app (import the bundle from Hugging Face inside the app) or through the LiteRT-LM Kotlin API; the same bundle also runs on iOS, macOS, Linux and Windows. The model card lists the measured speeds and the run commands.

In summary, Phi-3-mini opens up exciting possibilities for generative AI on edge devices, and you can start exploring its capabilities on Android.