83 comments

[ 2.3 ms ] story [ 69.9 ms ] thread
A year ago this would have been considered impossible. The hardware is moving faster than anyone's software assumptions.
The software has real software engineers working on it instead of researchers.

Remember when people were arguing about whether to use mmap? What a ridiculous argument.

At some point someone will figure out how to tile the weights and the memory requirements will drop again.

It wasn't considered impossible. There are examples of large MoE LLMs running on small hardware all over the internet, like giant models on Raspberry Pi 5.

It's just so slow that nobody pursued it seriously. It's fun to see these tricks implemented, but even on this 2025 top spec iPhone Pro the output is 100X slower than output from hosted services.

I mean, by any reasonable standard it still is. Almost any computer can run an llm, it's just a matter of how fast, and 0.4k/s (peak before first token) is not really considered running. It's a demo, but practically speaking entirely useless.
Does iPhone have some kind of hardware acceleration for neural netwoeks/ai ?
/FIFY A year ago this would have been considered impossible. The software is moving faster than anyone's hardware assumptions.
It's crazy to see a 400B model running on an iPhone. But moving forward, as the information density and architectural efficiency of smaller models continue to increase, getting high-quality, real-time inference on mobile is going to become trivial.
> moving forward, as the information density and architectural efficiency of smaller models continue to increase

If they continue to increase.

Probably 2x speed for Mac Studio this year if they do double NAND ( or quad?)
> SSD streaming to GPU

Is this solution based on what Apple describes in their 2023 paper 'LLM in a flash' [1]?

1: https://arxiv.org/abs/2312.11514

A similar approach was recently featured here: https://news.ycombinator.com/item?id=47476422 Though iPhone Pro has very limited RAM (12GB total) which you still need for the active part of the model. (Unless you want to use Intel Optane wearout-resistant storage, but that was power hungry and thus unsuitable to a mobile device.)
This is not entirely dissimilar to what Cerebus does with their weights streaming.
It’s 400B but it’s mixture of experts so how many are active at any time?
Aren't most companies doing MoE at this point?
Apple might just win the AI race without even running in it. It's all about the distribution.
Apple is already one of the winners of the AI race. It’s making much more profit (ie it ain’t losing money) on AI off of ChatGPT, Claude, Grok (you would be surprised at how many incels pay to make AI generated porn videos) subscriptions through the App Store.

It’s only paying Google $1 billion a year for access to Gemini for Siri

Because someone managed to run LLM on an iPhone at unusable speed Apple won AI race? Yeah, sure.
Run an incredible 400B parameters on a handheld device.

0.6 t/s, wait 30 seconds to see what these billions of calculations get us:

"That is a profound observation, and you are absolutely right ..."

This is awesome! How far away are we from a model of this capability level running at 100 t/s? It's unclear to me if we'll see it from miniaturization first or from hardware gains
I have some macro opinions about Apple - not sure if I'm correct, but tell me what you think.

Apple has always seen RAM as an economic advantage for their platform: Make the development effort to ensure that the OS and apps work well with minimal memory and save billions every year in hardware costs. In 2026, iPhones still come with 8Gb of RAM, Pro/Max come with 12Gb.

The problem is that AI (ML/LLM training and inference) are areas where you can't get around the need for copious amounts of fast working memory. (Thus the critical shortage of RAM at the moment as AI data centers consume as many memory chips as possible.)

Unless there's something I don't know (which is more than possible) Apple can't code their way around this problem, nor create specialized SoCs with ML cores that obviate the need for lots and lots of RAM.

So, it's going to be interesting whether they accept this reality and we start seeing the iPhones in the future with 16Gb, 32Gb or more as standard in order to make AI performant. And if they give up on adding AI to the billions of iPhones with minimal RAM already out there.

As a side note, 8Gb of RAM hasn't been enough for a decade. It prevents basic tasks like keeping web tabs live in the background. My pet peeve is having just a few websites open, and having the page refresh when swapping between them because of aggressive memory management.

To me, Apple's obvious strength is pushing AI to the edge as much as possible. While other companies are investing in massive data centers which will have millions of chips that will be outdated within the next couple years, Apple will be able to incrementally improve their ML/AI features by running on the latest and greatest chips every year. Apple has a huge advantage in that they can design their chips with a mega high speed bus, which is just as important as the quantity of RAM.

But all that depends on Apple's willingness to accept that RAM isn't an area they can skimp on any more, and I'm not sure they will.

Sorry for the brain dump. I'd love to be educated on this in case I'm totally off base.

CPU, memory, storage, time tradeoffs rediscovered by AI model developers. There is something new here, add GPU to the trade space.
It will be funny if we go back to lugging around brick-size batteries with us everywhere!
Impressive. Running a 400B model on-device, even at low throughput, is pretty wild.
Apple’s unified memory architecture plays a huge part in this. This will trigger a large scale rearchitecture of mobile hardware across the board. I am sure they are already underway.

I understand this is for a demo but do we really need a 400B model in the mobile? A 10B model would do fine right? What do we miss with a pared down one?

My iPad Air with M2 can run local LLMs rather well. But it gets ridiculously hot within seconds and starts throttling.
The power draw is going to be crazy (today).

Practical LLMs on mobile devices are at least a few years away.

"400 bytes should be enough for anybody"
I can't understand why this is a surprise to anyone. An iphone is still a computer, of course it can run any model that fits in storage albiet very slowly. The implementation is impressive I guess but I don't see how this is a novel capability. And for 0.6t/s, its not a cost efficient hardware for doing it. The iphone can also render pixar movies if you let it run long enough, mine bitcoin with a pathetic hashrate, and do weather simulations but not in time for the forecast to be relevant.
I installed Termux on an old Android phone last week (running LineageOS), and then using Termux installed Ollama and a small model. It ran terribly, but it did run.