Gemma 4 on iPhone • Hacker News Board

Re: Gemma 4 on iPhone

#241

Post by victorbjorklund » Mon, Apr 06, 2026, 4:20 PM UTC

mbesto wrote: post #227

victorbjorklund wrote: post #209

Earlier quoted context omitted.

You can look at open source models hosted by various companies that have no reason to host them on a loss.

Uber ran their ridesharing at a loss for years. This is a very common way to gain market share.

What market share? We are talking commodity models where the host does not matter at all at OpenRouter etc.

Re: Gemma 4 on iPhone

#242

Post by bigyabai » Mon, Apr 06, 2026, 4:47 PM UTC

amai wrote: post #234

The cooperation of Apple and Google is going to crush the competition: https://blog.google/company-news/inside-google/company-annou... The combination of Apples hardware and Googles software is unbeatable.

With Google's graveyard and Apple's walled garden, nothing can stop the enshittification train from trundling down the tracks.

Re: Gemma 4 on iPhone

#243

Post by sshrajesh » Mon, Apr 06, 2026, 4:50 PM UTC

> Note: I tried to hook this one up to OpenClaw and ran into issues

Anyone worked on hooking up OpenClaw to gemma4 running locally?

Re: Gemma 4 on iPhone

#244

Post by 3abiton » Mon, Apr 06, 2026, 5:25 PM UTC

deckar01 wrote: post #34

It doesn’t render Markdown or LaTeX. The scrolling is unusable during generation. E4B failed to correctly account for convection and conduction when reasoning about the effects of thermal radiation (31b was very good). After 3 questions in a session (with thinking) E4B went off the rails and started emitting nonsense fragment before the stated token limit was hit (unless it isn’t actually checking).

They have very limited capabilities compared to bigger more complex models, but for general stuff, they are fantastic. We need to set the expectations correctly of what they can do, I know lots of hype around Gemma 4, even though Qwen3.5 outperformed it. It's just a reliable overall small model, with great small model abilities.

Re: Gemma 4 on iPhone

#245

Post by Shawnj2 » Mon, Apr 06, 2026, 5:27 PM UTC

zozbot234 wrote: post #103

dimmke wrote: post #97

Earlier quoted context omitted.

I haven't seen anybody else post it in this thread, but this is running on 8GB of RAM. It's not the full Gemma 4 32B model. It's a completely different thing from the full Gemma 4 experience if you were running the flagship model, almost to the point of being misleading. It's their E2B and E4B variants (so 2B and 4B but also quantized) https://ai.google.dev/gemma/docs/core/model_card_4#dense_mod...

The relevant constraint when running on a phone is power, not really RAM footprint. Running the tiny E2B/E4B models makes sense, this is essentially what they're designed for.

Depends on the phone, I have trouble fitting models into memory on my iPhone 13 before iOS kills the app. I imagine newer phones with more RAM don’t have this issue especially with some new flagship phones having 16+ GB of memory

Re: Gemma 4 on iPhone

#246

Post by areys » Mon, Apr 06, 2026, 6:41 PM UTC

[flagged]

Re: Gemma 4 on iPhone

#247

Post by selfsigned » Mon, Apr 06, 2026, 7:04 PM UTC

kaliqt wrote: post #237

selfsigned wrote: post #196

Earlier quoted context omitted.

Two (very quick) minutes on their GitHub repo and it's pretty obvious that they're using firebase-analytics and at the very least seem to be sending URLs[1] and infos such as the model you download or the capacities[2] you use. [1] https://github.com/google-ai-edge/gallery/blob/main/Android/... [2] https://github.com/google-ai-edge/gallery/blob/main/Android/...

That’s not the same app as posted which is for iOS.

You're right, they reference IOS in the README.md and link to the GitHub repo from the Apple Store page yet don't include the IOS source, sneaky.

Re: Gemma 4 on iPhone

#248

Post by lemonish97 » Mon, Apr 06, 2026, 7:14 PM UTC

I hope they add a web search tool to the agent skills too. Most of my llm usage on my phone are just quick lookups and search summarizations. Would love to do these with a local model rather than Google AI mode of any other cloud based inference tools.

Re: Gemma 4 on iPhone

#249

Post by lemonish97 » Mon, Apr 06, 2026, 7:18 PM UTC

amai wrote: post #234

The cooperation of Apple and Google is going to crush the competition: https://blog.google/company-news/inside-google/company-annou... The combination of Apples hardware and Googles software is unbeatable.

Isn't their competition (at least in the mobile space) google/android themselves?

Re: Gemma 4 on iPhone

#250

Post by seivan » Mon, Apr 06, 2026, 7:59 PM UTC

humanperhaps wrote: post #201

nothinkjustai wrote: post #165

Earlier quoted context omitted.

Yeah definitely a skill issue downloading and running the app and it crashing on startup. Just gotta skillfully press the icon I guess.

Out of curiosity, do you have anything running on port 8000? Maybe it's not gracefully handling a port collision.

[dead]