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 4 hours ago | parent | next [-]

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 4 hours ago | parent [-]

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 30 minutes ago \| parent [-]
		It absolutely is RAM… So much so that this was what made Apple increase their base sizes.

▲

shtack an hour ago | parent | prev | next [-]

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

▲

1f60c 5 hours ago | parent | prev [-]

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