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

iPhone 17 Pro Demonstrated Running a 400B LLM

twitter.com

Post reply on HN
Print view View original

331–340 of 362 posts

Re: iPhone 17 Pro Demonstrated Running a 400B LLM

#331

Post by plussed_reader »

noemit wrote: post #317
cmiles8 wrote: post #291

To the extent that the present LLM movement reaches a steady state conclusion it’s highly likely to be open source models on your own hardware that are “good enough” for 95% of use cases. That blows up the whole “industrial complex” being developed around massive data centers, proprietary models, and everything that goes with that. Complete implosion. Apple has sat on the sidelines for much of this as it seems clear…

Even if it runs, this will run slowly, and heat up. I think local will always have a place, but the infrastructure is going to be used in my humble opinion.

I don't want to put information into a black box of mystery that can then be used for other monetization purposes. I am still waiting for a realistic local solution.

Re: iPhone 17 Pro Demonstrated Running a 400B LLM

#332

Post by latexr »

You can really feel the sycophantic drivel when it’s coming at 0.6 tokens per second.

> That is a profound observation, and you are absolutely right

Twenty seconds and a hot phone for that.

In the end it took almost four minutes to generate under 150 tokens of nothing.

Impressive that they got it to run, but that’s about the only thing.

Re: iPhone 17 Pro Demonstrated Running a 400B LLM

#333

Post by dudefeliciano »

latexr wrote: post #328
dudefeliciano wrote: post #307

Earlier quoted context omitted.

there is a case to be made that all AI company logos are just drawings of assholes: https://velvetshark.com/ai-company-logos-that-look-like-butt...

That’s a huge stretch. It’s calling anything remotely circular a butthole. Was that even written by a human? > OpenAI's original logo was a simple, text-based mark. Then came the redesign: a perfect circle with a subtle gradient and central void. The redesign is neither a circle nor does it have a gradient.

"PS. This post is meant to be humorous, but let's not pretend there isn't a serious point here about the depressing sameness in modern design. No actual anuses were consulted during this research, though several designers were clearly thinking about them."

> Was that even written by a human?

https://velvetshark.com/

Re: iPhone 17 Pro Demonstrated Running a 400B LLM

#335

Post by marci »

mike_hearn wrote: post #311
draxil wrote: post #298

Earlier quoted context omitted.

I assume you mean open weight models? I wish we had better open source models. It would make LLMs far less icky if we had nice clean open trained models. A breakthrough on the cost of training would be nice.

Nemotron is genuinely open source at least at the smaller sizes. You can download the datasets.

Also everything from scratch by allen.ai.

Weights, datasets, code, multiple checkpoints...

I like their FlexOlmo concept.

Re: iPhone 17 Pro Demonstrated Running a 400B LLM

#336

Post by throwaway173738 »

noemit wrote: post #317
cmiles8 wrote: post #291

To the extent that the present LLM movement reaches a steady state conclusion it’s highly likely to be open source models on your own hardware that are “good enough” for 95% of use cases. That blows up the whole “industrial complex” being developed around massive data centers, proprietary models, and everything that goes with that. Complete implosion. Apple has sat on the sidelines for much of this as it seems clear…

Even if it runs, this will run slowly, and heat up. I think local will always have a place, but the infrastructure is going to be used in my humble opinion.

Compute evolved from batch systems with time sharing to responsive systems in your pocket. Why wouldn’t that happen here?

Re: iPhone 17 Pro Demonstrated Running a 400B LLM

#337

Post by yencabulator »

BoorishBears wrote: post #250
yencabulator wrote: post #248

Qwen3.5-397B-A17B behaves more like a 17B parameter model. Omitting the MoE part from the headline makes it a lie and stupid hype. Quantizing is also a cheat code that makes the numbers lie, next up someone is going to claim running a large model when they're running a 1-bit quantization of it.

It behaves more like a ~80B parameter model (geometric mean of active and total params), and has world knowledge closer to a 400B parameter model There's no misleading here, they show every detail from model to quantization to that atrocious time to first token. Stuff like this feels more like code golf than anyone claiming the mainstream phone user is going to even download 100GB of model weights.

I think we're using different meaning of "behaves like". I meant "has tokens/sec performance comparable to".

Re: iPhone 17 Pro Demonstrated Running a 400B LLM

#339

Post by iLemming »

parineum wrote: post #329
iLemming wrote: post #261

Earlier quoted context omitted.

The Anthropic logo is just Kurt Vonnegut’s drawing of an asshole: https://scienceleadership.org/thumbnail/34729/1920x1920 Just in case if someone still didn't realize - we do live in Idiocracy https://www.youtube.com/watch?v=gGlJgU9x8tM

Their logo appears to be A\ ?

I misspoke. I meant of course to say "Claude's logo"

Re: iPhone 17 Pro Demonstrated Running a 400B LLM

#340

Post by latexr »

dudefeliciano wrote: post #333
latexr wrote: post #328

Earlier quoted context omitted.

That’s a huge stretch. It’s calling anything remotely circular a butthole. Was that even written by a human? > OpenAI's original logo was a simple, text-based mark. Then came the redesign: a perfect circle with a subtle gradient and central void. The redesign is neither a circle nor does it have a gradient.

"PS. This post is meant to be humorous, but let's not pretend there isn't a serious point here about the depressing sameness in modern design. No actual anuses were consulted during this research, though several designers were clearly thinking about them." > Was that even written by a human? https://velvetshark.com/

> This post is meant to be humorous

Was anyone supposed to think a post about comparing logos to buttholes was meant to be serious? Either way, the joke doesn’t work if what you’re describing makes no sense (circle and gradient) and are stretching the definition to unrecognizability.

> > Was that even written by a human?

> https://velvetshark.com/

So, probably not:

> I build AI agent systems and help companies implement AI that works in practice

> OpenClaw maintainer

> I make YouTube videos about AI workflows, agent architecture, and practical automation

Post reply on HN