Gemma 4 on iPhone
by janandonly on 4/5/2026, 6:45:53 PM
https://apps.apple.com/nl/app/google-ai-edge-gallery/id6749645337
Comments
by: pmarreck
Impressive model, for sure. I've been running it on my Mac, now I get to have it locally in my iPhone? I need to test this. Wait, it does agent skills and mobile actions, all local to the phone? Whaaaat? (Have to check out later! Anyone have any tips yet?)<p>I don't normally do the whole "abliterated" thing (dealignment) but after discovering <a href="https://github.com/p-e-w/heretic" rel="nofollow">https://github.com/p-e-w/heretic</a> , I was too tempted to try it with this model a couple days ago (made a repo to make it easier, actually) <a href="https://github.com/pmarreck/gemma4-heretical" rel="nofollow">https://github.com/pmarreck/gemma4-heretical</a> and... Wow. It worked. And... Not having a built-in nanny is <i>fun</i>!<p>It's also possible to make an MLX version of it, which runs a little faster on Macs, but won't work through Ollama unfortunately. (LM Studio maybe.)<p>Runs great on my M4 Macbook Pro w/128GB and likely also runs fine under 64GB... smaller memories might require lower quantizations.<p>I specifically like dealigned local models because if I have to get my thoughts policed when playing in someone else's playground, like hell am I going to be judged while messing around in my own local open-source one too. And there's a whole set of ethically-justifiable but rule-flagging conversations (loosely categorizable as things like "sensitive", "ethically-borderline-but-productive" or "violating sacred cows") that are now possible with this, and at a level never before possible until now.<p>Note: I tried to hook this one up to OpenClaw and ran into issues<p>To answer the obvious question- Yes, this sort of thing enables bad actors more (as do many other tools). Fortunately, there are far more good actors out there, and bad actors don't listen to rules that good actors subject themselves to, anyway.
4/5/2026, 7:38:16 PM
by: burnto
My iPhone 13 can’t run most of these models. A decent local LLM is one of the few reasons I can imagine actually upgrading earlier than typically necessary.
4/5/2026, 8:41:59 PM
by: PullJosh
This is awesome!<p>1) I am able to run the model on my iPhone and get good results. Not as good as Gemini in the cloud, but good.<p>2) I love the “mobile actions” tool calls that allow the LLM to turn on the flashlight, open maps, etc. It would be fun if they added Siri Shortcuts support. I want the personal automation that Apple promised but never delivered.<p>3) I am so excited for local models to be normalized. I build little apps for teachers and there are stringent privacy laws involved that mean I strongly prefer writing code that runs fully client-side when possible. When I develop apps and websites, I want easy API access to on-device models for free. I know it sort of exists on iOS and Chrome right now, but as far as I’m aware it’s not particularly good yet.
4/5/2026, 7:41:44 PM
by: janandonly
OP Here. It is my firm belief that the only realistic use of AI in the future is either locally on-device for almost free, or in the cloud but way more expensive then it is today.<p>The latter option will only bemusedly for tasks that humans are more expensive or much slower in.<p>This Gemma 4 model gives me hope for a future Siri or other with iPhone and macOS integration, “Her” (as in the movie) style.
4/5/2026, 8:37:08 PM
by: jeroenhd
English version of the page: <a href="https://apps.apple.com/us/app/google-ai-edge-gallery/id6749645337">https://apps.apple.com/us/app/google-ai-edge-gallery/id67496...</a><p>Also on Android: <a href="https://play.google.com/store/apps/details?id=com.google.ai.edge.gallery">https://play.google.com/store/apps/details?id=com.google.ai....</a><p>It's a demo app for Google's Edge project: <a href="https://ai.google.dev/edge" rel="nofollow">https://ai.google.dev/edge</a>
4/5/2026, 7:51:10 PM
by: dwa3592
I think with this google starts a new race- best local model that runs on phones.
4/5/2026, 8:38:28 PM
by: TGower
These new models are very impressive. There should be a massive speedup coming as well, AI Edge Gallery is running on GPU, but NPUs in recent high end processors should be much faster. A16 chip for example (Macbook Neo and iphone 16 series) has 35 TOPS of Neural Engine vs 7 TFLOPS gpu. Similar story for Qualcomm.
4/5/2026, 8:09:46 PM
by: hadrien01
Is it me or does the App Store website look... fake? The text in the header ("Productiviteit", "Alleen voor iPhone") looks pixelated, like it was edited on Paint, the header background is flickering, the app icon and screenshots are very low quality, the title of the website is incomplete ("App Store voor iPho...")
4/5/2026, 7:31:12 PM
by:
4/5/2026, 7:55:46 PM
by: carbocation
It would be very helpful if the chat logs could (optionally) be retained.
4/5/2026, 8:00:24 PM
by: darshil2023
[dead]
4/5/2026, 7:05:50 PM