100% On-Device Execution
Runs GGUF models natively via llama.cpp compiled
with the Android NDK. Your prompts and responses stay on your
device.
SmolChat lets you run Small Language Models (SLMs) in GGUF format
directly on your Android device using llama.cpp—no
cloud APIs, no internet required, and full control over prompts
and inference parameters.
Designed around a clean Android interface and native C/C++ execution for fast, private conversations on your phone.
Runs GGUF models natively via llama.cpp compiled
with the Android NDK. Your prompts and responses stay on your
device.
Add, remove, and switch between local GGUF models, or download models directly inside the app.
Configure system prompts, temperature, and min-p
per chat or set global defaults for all new conversations.
Create reusable single-turn tasks for quick text generation without persisting chat history.
Renders rich Markdown responses with Markwon and Prism4j, complete with one-tap copy for code blocks.
Includes a local HTTP server capable of listing loaded models and serving OpenAI-compatible LLM inference.
Explore the chat experience, model management, and inference settings on Android.
Choose the distribution channel that works best for you.
Install directly from the Google Play Store with automatic updates.
https://github.com/shubham0204/SmolChat-Android
Visualizing how prompts flow from the Android UI down to native GGUF inference.