JackZeng0208/llama.cpp-android-tutorial

llama.cpp tutorial on Android phone

40
/ 100
Emerging

This project guides developers through the process of setting up and running large language models (LLMs) like Llama directly on Android phones equipped with Qualcomm Snapdragon processors. It shows how to compile the `llama.cpp` library to leverage the phone's Adreno GPU for faster processing. The output is a functional `llama.cpp` application, potentially integrated with Python, capable of performing local LLM inference on the device. This is for Android app developers or researchers interested in deploying and evaluating LLMs on mobile hardware.

155 stars. No commits in the last 6 months.

Use this if you are a developer looking to deploy and run large language models directly on an Android device with a Qualcomm Snapdragon SoC, utilizing its Adreno GPU for accelerated performance.

Not ideal if you are a general user wanting a ready-to-use LLM app, or if your Android device does not have a Qualcomm Snapdragon processor with an Adreno GPU.

mobile-LLM-deployment on-device-AI Android-development mobile-machine-learning edge-AI
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 12 / 25

How are scores calculated?

Stars

155

Forks

12

Language

License

MIT

Last pushed

May 02, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/JackZeng0208/llama.cpp-android-tutorial"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.