[PullJosh]

This is awesome!

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.

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.

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.

[buzzerbetrayed]

For me the hallucination and gaslighting is like taking a step back in time a couple of years. It even fails the “r’s in strawberry” question. How nostalgic.

It’s very impressive that this can run locally. And I hope we will continue to be able to run couple-year-old-equivalent models locally going forward.

[dimmke]

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...

[zozbot234]

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.

[trvz]

It absolutely is RAM…

So much so that this was what made Apple increase their base sizes.

[Shawnj2]

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

[bigyabai]

Between the GPU, NPU and big.LITTLE cores, many phones have no fewer than 4 different power profiles they can run inference at. It's about as solved as it will get without an architectural overhaul.

[1f60c]

Strangely, reasoning is not on by default. If you enable it, it answers as you'd expect.

[shtack]

With reasoning on I found E4B to be solid, but E2B was completely unusable across several tests.