MobileLLM Android

MobileLLM

Chatbot, running with Llama 3.3, DeepSeek-R1, Gemma 3, qwen, mistral locally.

Features & Capabilities

MobileLLM running with Llama 3.3, DeepSeek-R1, Gemma 3, Phi and other popular large language models on your phone, you can chat with LLM locally and privately without network.

Support vision model like Gemma 3, llava.

Be a little patient when downloading big models.

Key Features:

- Offline Chatting: Interact with advanced AI models directly on your device without the need for an internet connection.
- Popular LLM model integerated: Llama 3.3, DeepSeek-R1, Phi-4, Gemma 3, llava, mistral
- Text to speech, speak the response as you will.
- Chat history saved on your phone, no any data upload to Internet for your privacy.

User Growth & Download Statistics

App
By:
Playstar
Downloads:
567 24
Version:
1.0.0 Last updated: 2025-04-10
Version code:
1
Creation date:
2025-04-09
Publisher country:
CN CN
Permissions:
  • com.google.android.gms.permission.AD_ID Moderate risk
  • android.permission.ACCESS_ADSERVICES_AD_ID Low risk
  • android.permission.ACCESS_ADSERVICES_ATTRIBUTION Low risk
  • android.permission.ACCESS_ADSERVICES_TOPICS Low risk
  • android.permission.FOREGROUND_SERVICE Low risk
  • android.permission.INTERNET Low risk
  • android.permission.WAKE_LOCK Low risk
  • android.permission.ACCESS_NETWORK_STATE Safe
  • com.android.vending.CHECK_LICENSE Safe
  • android.permissions.WRITE_EXTERNAL_STORAGE
  • See more
Size:
53.48MB
Email:
pl*****@gmail.com
URLs:
Website ,Privacy policy
Full description:
See detailed description
Source:
Google Play Store
Data ingested on:
2026-06-03
Compare stats and ranking:

Contact the developer

Chrome-Stats does not own this Android app. Please use these information below to contact the Android app developer.
Developed by:
Playstar
Google Play Store
https://play.google.com/store/apps/details?id=dev.speedx.mobilellm
Email:
pl*****@gmail.com
Website:
https://speedx.dev

Best MobileLLM Alternatives

Here are some Android apps that are similar to MobileLLM: