Off Grid - Private AI Chat

3.7
103 reviews
10K+
Downloads
Content rating
Everyone
Screenshot image
Screenshot image
Screenshot image
Screenshot image
Screenshot image
Screenshot image
Screenshot image
Screenshot image

About this app

Your phone is powerful enough to run AI. Why send your data to someone else's server?

Off Grid runs AI entirely on your device. No internet required. No accounts. No subscriptions. No data ever leaves your phone.

WHAT YOU CAN DO
- Chat with AI - Run Llama, Qwen, Gemma, Phi and other open models
- Generate images - Stable Diffusion running on your phone's NPU
- Vision AI - Point your camera at anything and ask questions
- Voice input - Whisper transcription, completely offline
- Attach documents - Analyze PDFs, code, text files privately

WHY OFF GRID
- 100% offline after downloading models
- Your conversations never leave your device
- No cloud costs, no API limits, no subscriptions
- Works on airplane mode
- Open source (MIT licensed)

PERFORMANCE
- 15-30 tokens/sec text generation on flagship devices
- 5-10 second image generation with NPU acceleration
- Supports GPU offloading for faster inference

PRIVACY FIRST
Use AI for sensitive tasks you'd never trust to the cloud - journal entries, health questions, work notes, personal photos. Your data stays yours.

Download a model, go offline, and never look back.
Updated on
Apr 8, 2026

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

3.6
99 reviews
Conall O'Shannessy
April 4, 2026
App is actually awesome. The only reason I gave it 3 stars is because it throws an error for tools on almost every model I use on my server. For vanilla qwen or using small models on phones its fine. But it needs a disable tools toggle so we can use any server model without this limitation. Happy to update to 5 stars if fixed, or if I missed the setting. cheers
1 person found this review helpful
Did you find this helpful?
Beta Solutions
April 7, 2026
I'll work on this and get it out soon
Sebastián González
March 2, 2026
Pretty interesting! I like the design of the app and most of the things make sense. One that didn't (or I couldn't figure out) was loading an t2i model without relying on loading a text model first. As for custom models, I tried a GGUF of qwen 3.5 0.8b and it failed to load. Unsure on what to do and how and where the app pulls versions. Apart from that, it's phenomenal. Long live local AI! Ps. Streaming the text as it generates would be cool. It only shows the answer after it reaches 100%
4 people found this review helpful
Did you find this helpful?
Beta Solutions
March 4, 2026
hey, the app should be streaming the text and not only showing it when its done. Could you join here: https://tinyurl.com/498pxd22 I'll help you out. Most of the things you've raised should already be working. Maybe it is feedback for me from a UI/UX perspective. Would love to talk to you
Cursed Narrations
March 27, 2026
My time with it has been great the text models work perfectly but I would like a smaller image model the ones provided are just to big for my android but otherwise best app I've experienced in the private ai space. edit:had to drop it a star because I had to delete damn near everything on my phone and the image models are saying I cant use them after downloading them because it will take 2 gigabytes to use and saying I only have 1.6 to safely use
Did you find this helpful?

What’s new

Gemma 4 support added. Smart model sorting with "For You" and trending recommendations based on your device. Vision model import overhauled with automatic mmproj linking and an in-app repair flow. Downloads now run as a foreground service on Android — no more throttling. Multi-file vision model import supported. Conversations start only when you send your first message.

App support

About the developer
Mohammed Ali Chherawalla
mohammed.ali.chherawalla@gmail.com
India