2.7
66 reviews
5K+
Downloads
Content rating
Everyone
Screenshot image
Screenshot image
Screenshot image
Screenshot image
Screenshot image
Screenshot image
Screenshot image
Screenshot image
Screenshot image
Screenshot image
Screenshot image
Screenshot image
Screenshot image
Screenshot image

About this app

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.
Updated on
Sep 19, 2025

Data safety

Safety starts with understanding how developers collect and share your data. Data privacy and security practices may vary based on your use, region, and age. The developer provided this information and may update it over time.
No data shared with third parties
Learn more about how developers declare sharing
No data collected
Learn more about how developers declare collection

Ratings and reviews

3.1
60 reviews
Z X
August 27, 2025
I wanted to try a Bitnet model. dowloaded MS ggml-model-i2_s.gguf and Rushi2901's version but none of them work. App is just quitting during download however both have about 1G size. In another app i have successfuly tried a 7B model however it was too slow. GUI is great, but it would be great not no import large files just use from the location they are placed like SD card. I don't have too much free internal space.
Did you find this helpful?
Wavy Gravy
September 29, 2025
Excellent.. and free... however when the LLM is answering, and you turn your phone from portrait to landscape, the reply is lost and perhaps forgotten. It's fine once it's finished answering.
1 person found this review helpful
Did you find this helpful?
Michael Walsh
December 3, 2025
for the supported models, it's pretty good. doesn't seem to work for unlisted gguf files, but that's not advertised, so that's okay.
Did you find this helpful?

What’s new

- Fixed a bug where the app's memory usage kept increasing after switching models i.e. the memory acquired by the previous model was not 'released' when selecting a different model
- Align default inference parameters with those found in `llama` executable

UI Improvements:
- Chat message actions like share/copy/edit are now available in a dialog which appears when the message is long-pressed
- Preserve query text in the search box when a model is opened while browsing HuggingFace