News for hackers. Stuff that matters.

ali_chherawalla

You may not need $25k. Off Grid AI runs open models on the desktop/laptop you already have and picks ones that fit its memory, free and offline. Bigger ones run on your desktop and you can use them from your phone without any cloud servers in between. either your wifi or a tailnet like tailscale
appreciate it!

Show HN: OGAC – Run reliable, compliant and governed AI for your enterprise

https://onprem-console.getoffgridai.co

Frontier models makes ICs productive with AI. OGAC makes the entire enterprise productive with AI.It combines the company moat i.e context, data, processes, and people with the innovation and excellence of frontier models while ensuring safety, compliance, observability and governance.It's built on top of the best of open source products, and contains the layer that talks to all of these...

( Read More... | 2 comments | 2 points | on HN )
yeah seems pretty insane!
Thats pretty interesting. with what is possible with openweight models now, having this multimodal functionality on your device itself will be quite next level
understood.
I'm curious what the point is though?
this is super interesting. Looking forward to trying this out!
Healthcare has the strictest compliance requirements of any US industry. The most sensitive data. Twenty-five new state AI regulations introduced this year alone.

It also has the largest gap between AI deployment and AI governance of any sector we looked at.

Three out of four US health systems are running AI in 2026. Less than one in five has governed it. That is not a laggard industry failing to adopt — it is an industry that adopted faster than it figured out what it was doing. The compliance exposure sitting inside most health systems right now is not hypothetical. It is running in production.

We mapped this across financial services, healthcare, energy, manufacturing, and logistics. Healthcare was the one that made us stop.

Full report: https://mobile.wednesday.is/the-enterprise-mobile-ai-report-...

Show HN: Find out if your SaaS is underpriced in 10 minutes

https://github.com/wednesday-solutions/rightsuite.co

GTM iteration is slow by nature. Test the price, wrong. Fix the message, doesn't convert. Try a new audience, wrong segment. Pick a channel, no traction. Each mistake costs a month. By the time you've iterated to something that works, the market has moved - especially now, when AI is reshaping what buyers want every quarter.We built RightSuite to compress that cycle. Describe your offer and...

( Read More... | 2 comments | 5 points | on HN )
awesome. I'll let you know once thats in
fair point, let me know work on that. That's a small lift.
lol thanks buddy!
I'm working on that we speak. Shouldn't not be that difficult of a lift and should be able to do that tonight or in the next couple of nights
ofcourse ofcourse,

I've documented everything here: https://github.com/alichherawalla/off-grid-mobile-ai/blob/ma...

llama.cpp compiled as a native Android library via the NDK, linked into React Native through a custom JSI bridge. GGUF models loaded straight into memory. On Snapdragon devices we use QNN (Qualcomm Neural Network) for hardware acceleration. OpenCL GPU fallback on everything else. CPU-only as a last resort.

Image gen is Stable Diffusion running on the NPU where available. Vision uses SmolVLM and Qwen3-VL. Voice is on-device Whisper.

The model browser filters by your device's RAM so you never download something your phone can't run. The whole thing is MIT licensed - happy to answer anything about the architecture.

Show HN: Qwen 3.5 running on a $300 Android phone – on-device, open source

https://github.com/alichherawalla/off-grid-mobile-ai/

Qwen 3.5 Small dropped two days ago. I had it running on a mid-tier Android phone within hours.It's great seeing the on-device AI community light up around this release. Off Grid brings it to Android: phones with 6GB RAM in the $200-300 range, ~8 tok/sec on the 2B model. Fully offline.Text generation, vision AI, image gen, voice transcription, tool calling, document analysis — all on-device,...

( Read More... | 10 comments | 3 points | on HN )
you're doing the marketing for me ahaha! appreciate it though. thank you
dude thats awesome to hear! I literally added support for web search, tool calling and KV cache optimization support + usage of all 99 GPU layers a few hours ago!

Those changes are not live on the play store / app store but its available on GH. I'll make a release later today.

Let me know what you think!

Show HN: Off Grid: On-device AI-web browsing, tools vision,image,voice–3x faster

Nine days ago I posted Off Grid here and you showed up - 124 points, 66 comments, bug reports I fixed same-day, and the kind of feedback that makes open source worth it.You told me what you wanted. Here's what I shipped: Your AI can now use tools — entirely offline.Web search, calculator, date/time, device info — with automatic tool loops.Your 3B parameter model doesn't just generate text...

( Read More... | 5 comments | 8 points | on HN )

Off Grid: On-device AI-web browsing, tools, vision, image gen, voice – 3x faster

Nine days ago I posted Off Grid here and you showed up - 124 points, 66 comments, bug reports I fixed same-day, and the kind of feedback that makes open source worth it.You told me what you wanted. Here's what I shipped: Your AI can now use tools - entirely offline.Web search, calculator, date/time, device info - with automatic tool loops.Your 3B parameter model doesn't just generate text...

( Read More... | 1 comment | on HN )
Off Grid is live on the playstore now. Check it out: https://play.google.com/store/apps/details?id=ai.offgridmobi...
I think thats a bug, I'm guessing you're trying one of the NPU models? If you drop to CPU for now it should hold.

Only phones with qualcomm chips are able to use the NPU. I'm working towards changing that.

but yeah just to be clear there is no internet needed to run any of this. Infact I'm so averse to it, I've not even added analytics for this one. So flying pretty blind here.

it doesn't need internet to generate an image. it needs it to download the model, and to be fair if you've got the zip for the model already you can just import that
awesome. thanks!
sure, I'll take a look at it. Thank you for the recommendation
awesome. The more the merrier. Feel free to get started.

I'm still working on a few things, but let me get a backlog in place and push it so people know what the roadmap looks like

hey! thank you for the feedback. appreciate it. I pushed something recently that actually prevents showing up models in the download screen that don't fit on your phone. Please give it a whirl.

Yeah it wasn't straight forward figuring out the speed + getting it to work for both Android and iOS. Fair bit if complexity. But I'm so happy I got it done.

Older »