sangaya2 hours ago
Putting the power and the data of the users in the hands of the users themselves! Well done. Getting it setup was easy. Wish the app recognized the keyboard and realized when it was displayed so the bottom menu and chat box weren't hidden under it.
ali_chherawalla1 hour ago
Thank you!
resonious3 hours ago
On my Samsung phone it doesn't move the screen up to make room for the keyboard so I can't see what I'm typing.

Really awesome idea though. I want this to work.

dotancohen2 hours ago
I can confirm this bug on a Samsung S24 Ultra.
ali_chherawalla1 hour ago
sorry about that one. I'm taking a look and fixing it right away
ali_chherawalla36 minutes ago
hey, just pushed a fix for it here: https://github.com/alichherawalla/off-grid-mobile/releases/t...

Thanks for spotting and reporting this.

nine_k2 hours ago
Is there something similar, but geared towards a Linux desktop / laptop? I suppose this would be relatively easy to adapt.
ali_chherawalla1 hour ago
LM Studio solves for it pretty well I think. It doesn't do image gen etc though
bkmeneguello4 hours ago
Very nice, but I'm gonna wait for the f-droid build.
ali_chherawalla1 hour ago
ok, let me figure that one out.
flyingkiwi444 hours ago
The repository is listed as offgrid-mobile everywhere on that page but is off-grid-mobile.

So the lastest releases is at https://github.com/alichherawalla/off-grid-mobile/releases/l...

And the clone would be: git clone https://github.com/alichherawalla/off-grid-mobile.git

ali_chherawalla1 hour ago
hey, yes. thanks just pushed that fix out
wittlesus1 hour ago
This is genuinely exciting. The fact that you're getting 15-30 tok/s for text gen on phone hardware is wild — that's basically usable for real conversations.

Curious about a couple things: what GGUF model sizes are practical on a mid-range phone (say 8GB RAM)? And how's the battery impact during sustained inference — does it drain noticeably faster than, say, a video call?

The privacy angle is the real killer feature here IMO. There are so many use cases (journaling, health tracking, sensitive work notes) where people self-censor because they know it's going to a server somewhere. Removing that barrier entirely changes what people are willing to use AI for.

durhamg1 hour ago
This sounds exactly like Claude wrote it. I've noticed Claude saying "genuinely" a lot lately, and the "real killer feature" segue just feels like Claude being asked to review something.
ali_chherawalla1 hour ago
I've added a section for recommended models. So basically you can chose from there.

I'd recommend going for any quantized 1B parameter model. So you can look at llama 3.2 1B, gemma3 1B, qwen3 VL 2B (if you'd like vision)

Appreciate the kind words!

add-sub-mul-div1 hour ago
> that's basically usable for real conversations.

That's using the word "real" very loosely.

vachina3 hours ago
Ok it lists the instruction to build for iOS, but how to sideload?
behole3 hours ago
ali_chherawalla1 hour ago
yeah thats right. for now for iOS you'll actually have to pod install etc.

Thanks for pointing this out

instagib2 hours ago
Wonder if you can use GitHub actions to build iOS.

I found a guide for virtual box macOS which failed on intel then another for hyper-V but haven’t tried that one yet.

derac4 hours ago
I haven't run it, but I looked through the repo. It looks very well thought out, the UI is nice. I appreciate the ethos behind the local/offline design. Cheers.
ali_chherawalla1 hour ago
thank you!
snicky4 hours ago
GitHub Releases link is broken.

The dash in "off-grid" is missing.

ali_chherawalla1 hour ago
yup, just took a look at that and fixed it. My bad!
chr15m1 hour ago
This rules. Godspeed!
ali_chherawalla1 hour ago
wow. thank you