Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Gemma 4 on iPhone

apps.apple.com

Post reply on HN
Print view View original

71–80 of 267 posts

Re: Gemma 4 on iPhone

#71

Post by bossyTeacher »

pmarreck wrote: post #8

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?) I don't normally do the whole "abliterated" thing (dealignment) but after discovering https://github.com/p-e-w/heretic , I was too tempted to try it with this mode…

>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.

Mind giving us a few of the examples that you plan to run in your local LLM? I am curious.

Re: Gemma 4 on iPhone

#72

Post by tredre3 »

spijdar wrote: post #31
barbazoo wrote: post #23

Earlier quoted context omitted.

> 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. I checked the abliterate script and I don't yet understand what it does or what the result is. What are the conversations this enables?

Realistically, a lot of people do this for porn. In my experience, though, it's necessary to do anything security related. Interestingly, the big models have fewer refusals for me when I ask e.g. "in situation, how do you exploit ?", but local models will frequently flat out refuse, unless the model has been abliterated.

From what I've seen gemma 4 doesn't refuse a lot regarding sex, it only needs little nudging in the right direction sometimes.

But it does refuse being critical of the usual topics: israel, islam, trans, or race.

So wanting to discuss one of those is the real reason people would use an uncensored model.

Re: Gemma 4 on iPhone

#73

Post by _pdp_ »

janandonly wrote: post #28

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. The latter option will only bemusedly for tasks that humans are more expensive or much slower in. This Gemma 4 model gives me hope for a future Siri or other with iPhone and macOS integration, “Her” (as in the movie) style.

If you can run free models on consumer devices why do you think cloud providers cannot do the same except better and bundled with a tone of value worth paying?

Re: Gemma 4 on iPhone

#75

Post by Mil0dV »

kgeist wrote: post #70
nkohari wrote: post #68

Earlier quoted context omitted.

You're comparing apples to oranges there. Qwen 3.5 is a much larger model at 397B parameters vs. Gemma's 31B. Gemma will be better at answering simple questions and doing basic automation, and codegen won't be it's strong suit.

Qwen3.5 comes in various sizes (including 27B), and judging by the posts on HN, /LocalLlama etc., it seems to be better at logic/reasoning/coding/tool calling compared to Gemma 4, while Gemma 4 is better at creative writing and world knowledge (basically nothing changed from the Qwen3 vs. Gemma3 era)

Does this also apply to gemma's 26B-A4B vs say Qwens 35B-A3B?

I'm not sure if I can make the 35B-A3B work with my 32GB machine

Re: Gemma 4 on iPhone

#77

Post by dhbradshaw »

My son just started using 2B on his Android. I mentioned that it was an impressively compact model and next thing I knew he had figured out how to use it on his inexpensive 2024 Motorolla and was using it to practice reading and writing in foreign languages.

Re: Gemma 4 on iPhone

#78

Post by gigatexal »

tredre3 wrote: post #69
nkohari wrote: post #68

Earlier quoted context omitted.

You're comparing apples to oranges there. Qwen 3.5 is a much larger model at 397B parameters vs. Gemma's 31B. Gemma will be better at answering simple questions and doing basic automation, and codegen won't be it's strong suit.

Gemma 4 31B is still not impressive at coding compare to even Qwen 3.5 27B. It's just not its strong suit. So far gemma 4 seems excellent at role playing, document analysis, and decent at making agentic decisions.

This has been my experience as well, Qwen via Ollama locally has been very very impressive.

Re: Gemma 4 on iPhone

#79

Post by peyton »

pmarreck wrote: post #61
barbazoo wrote: post #23

Earlier quoted context omitted.

> 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. I checked the abliterate script and I don't yet understand what it does or what the result is. What are the conversations this enables?

1) Coming up with any valid criticism of Islam at all (for some reason, criticisms of Christianity or Judaism are perfectly allowed even with public models!). 2) Asking questions about sketchy things. Simply asking should not be censored. 3) I don't use it for this, but porn or foul language. 4) Imitating or representing a public figure is often blocked. 5) Asking security-related questions when you are trying to do…

The manufacturing of biologics can be heavily censored to an absurd degree. I don’t know about Gemma 4 in particular.
Post reply on HN