SmolChat - On-Device Inference of SLMs in Android

Installation

Google Play

Get it on Google Play

GitHub

1. Download the latest APK from GitHub Releases and transfer it to your Android device.
2. If your device does not downloading APKs from untrusted sources, search for how to allow downloading APKs from unknown sources for your device.

Obtainium

Obtainium allows users to update/download apps directly from their sources, like GitHub or FDroid.

1. Download the Obtainium app by choosing your device architecture or ‘Download Universal APK’.
2. From the bottom menu, select ‘➕Add App’
3. In the text field labelled ‘App source URL *’, enter the following URL and click ‘Add’ besides the text field: https://github.com/shubham0204/SmolChat-Android
4. SmolChat should now be visible in the ‘Apps’ screen. You can get notifications about newer releases and download them directly without going to the GitHub repo.

Project Goals

• Provide a usable user interface to interact with local SLMs (small language models) locally, on-device
• Allow users to add/remove SLMs (GGUF models) and modify their system prompts or inference parameters (temperature,
  min-p)
• Allow users to create specific-downstream tasks quickly and use SLMs to generate responses
• Simple, easy to understand, extensible codebase

Setup

1. Clone the repository with its submodule originating from llama.cpp,

git clone --depth=1 https://github.com/shubham0204/SmolChat-Android
cd SmolChat-Android
git submodule update --init --recursive

2. Android Studio starts building the project automatically. If not, select Build > Rebuild Project to start a project build.

3. After a successful project build, connect an Android device to your system. Once connected, the name of the device must be visible in top menu-bar in Android Studio.

Working

1. The application uses llama.cpp to load and execute GGUF models. As llama.cpp is written in pure C/C++, it is easy
   to compile on Android-based targets using the NDK.

2. The smollm module uses a llm_inference.cpp class which interacts with llama.cpp’s C-style API to execute the
   GGUF model and a JNI binding smollm.cpp. Check the C++ source files here. On the Kotlin side, the SmolLM class provides
   the required methods to interact with the JNI (C++ side) bindings.

3. The app module contains the application logic and UI code. Whenever a new chat is opened, the app instantiates
   the SmolLM class and provides it the model file-path which is stored by the LLMModel entity.
   Next, the app adds messages with role user and system to the chat by retrieving them from the database and
   using LLMInference::addChatMessage.

4. For tasks, the messages are not persisted, and we inform to LLMInference by passing _storeChats=false to
   LLMInference::loadModel.

Technologies

• ggerganov/llama.cpp is a pure C/C++ framework to execute machine learning
  models on multiple execution backends. It provides a primitive C-style API to interact with LLMs
  converted to the GGUF format native to ggml/llama.cpp. The app uses JNI bindings to interact with a small class smollm. cpp which uses llama.cpp to load and execute GGUF models.

• noties/Markwon is a markdown rendering library for Android. The app uses
  Markwon and Prism4j (for code syntax highlighting) to render Markdown responses
  from the SLMs.

More On-Device ML Projects

• shubham0204/Android-Doc-QA: On-device RAG-based question
  answering from documents
• shubham0204/OnDevice-Face-Recognition-Android:
  Realtime face recognition with FaceNet, Mediapipe and ObjectBox’s vector database
• shubham0204/FaceRecognition_With_FaceNet_Android:
  Realtime face recognition with FaceNet, MLKit
• shubham0204/CLIP-Android: On-device CLIP inference in Android
  (search images with textual queries)
• shubham0204/Segment-Anything-Android: Execute Meta’s
  SAM model in Android with onnxruntime
• shubham0204/Depth-Anything-Android: Execute the
  Depth-Anything model in Android with onnxruntime for monocular depth estimation
• shubham0204/Sentence-Embeddings-Android: Generate
  sentence-embeddings (from models like all-MiniLM-L6-V2) in Android

Future

The following features/tasks are planned for the future releases of the app:

• Assign names to chats automatically (just like ChatGPT and Claude)
• Add a search bar to the navigation drawer to search for messages within chats
• Add a background service which uses BlueTooth/HTTP/WiFi to communicate with a desktop application to send queries
  from the desktop to the mobile device for inference
• Enable auto-scroll when generating partial response in ChatActivity
• Measure RAM consumption
• Integrate Android-Doc-QA for on-device RAG-based question answering from documents
• Check if llama.cpp can be compiled to use Vulkan for inference on Android devices (and use the mobile GPU)