SmolChat

io.shubham0204.smollmandroid

SmolChat allows you to download and run popular LLMs on your Android device, locally, without needing an internet connection. Customize the model used for each chat, tune settings like temperature and min-p, and pin your favourite chats on the home-screen with shortcuts.

First release: Nov 1, 2026, 1 total release.

Most recent release: Nov 1, 2026.

Repo

Appears in 0 app stacks.

0 sats / 0 zaps received in the past year.

Sats Received

Underlying data available via MCP: app_zaps, app_releases.

Zap Count

Underlying data available via MCP: app_zaps, app_releases.

Releases

Nov 1, 2026 17

- OpenAI-compatible HTTP server that could list models and perform LLM inference. - Added a button to copy code when code blocks are rendered in the chat. - Models are downloading directly instead of using the Android system's download service. - Optimized Markdown rendering to reduce CPU usage when rendering long chats. - Support global chat settings that are applicable to all new chats by default. - Fix measurement of tokens/sec in the chat. It now shows the token generation rather than accounting for prompt processing time. - min-p from chat settings is now passed to the llama.cpp - Sync with upstream llama.cpp