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

Apple M5 chip

apple.com

Post reply on HN
Print view View original

431–440 of 1001 posts

Re: Apple M5 chip

#431

Post by jsheard »

croes wrote: post #415
ironman1478 wrote: post #325

It's surprising to me macs aren't a more popular target for games. They're extremely capable machines and they're console-like in that there isn't very much variation in hardware, as opposed to traditional PC gaming. I would think that it's easier to develop a game for a MacBook than a Windows machine where you never know what hardware setup the user will have.

Doesn’t MacOS favor an 60Hz output? Gamers prefer much higher rates. And don’t forget they made an VR headset without controllers. Apple doesn’t care about games

> Doesn’t MacOS favor an 60Hz output?

Kind of? It does support higher refresh rates, but their emphasis on "Retina" resolutions imposes a soft limit because monitors that dense rarely support much more than 60hz, due to the sheer bandwidth requirements.

Re: Apple M5 chip

#432

Post by bigyabai »

GeekyBear wrote: post #311

I'd argue that calling the new matrix multiplication unit they added to the GPU cores a neural engine instead of a tensor processing unit is a branding error that will lead to confusion. The existing neural engine's function is to maximize power efficiency, not flexible performance on models of any size.

I'd argue that Apple's definition of "neural engine" was entirely different from what the greater desktop, edge and datacenter markets already considered a "neural engine" to be.

It's an improvement, nomenclature-wise.

Re: Apple M5 chip

#434

Post by cj »

paxys wrote: post #392

M5 is 4-6x more powerful than M4, which was 5x more powerful than M3, which was 4x more powerful than M2, which was 4x more powerful than M1, which itself was 6x faster than an equivalent Intel processor. Great! Looking at my Macbook though, I can say with utmost certainty that it isn't 4000x faster than the Intel one I had 5 years ago. So, where is the disconnect here? Why is actual user experience not able to keep…

I’m not sure I see the disconnect.

At our company we used to buy everyone MacBook Pros by default.

After the M-series chip, the MBPs are just too powerful and no longer necessary for the average white collar worker (they seem like “actual” pro machines, now) to the point where we now order MacBook Airs for new employees.

I feel like until recently, you really needed a MBP to get a decent UX (even just using chrome). But now there doesn’t seem to be a major compromise when buying an Air for half the price, at least compared to 3-5 years ago.

Re: Apple M5 chip

#435

Post by zozbot234 »

llm_nerd wrote: post #362
fooblaster wrote: post #176

Earlier quoted context omitted.

MLX doesn't use the neural engine still right? I still wish they would abandon that unit and just center everything around metal and tensor units on the GPU.

MLX is a training/research framework, and the work product is usually a CoreML model. A CoreML model will use any and all resources that are available to it, at least if the resource fits for the need. The ANE is for very low power, very specific inference tasks. There is no universe where Apple abandons it, and it's super weird how much anti-ANE rhetoric there is on this site, as if there can only be one tool for an…

> ...and it's super weird how much anti-ANE rhetoric there is on this site, as if there can only be one tool for an infinite selection of needs

That seems like a strange comment. I've remarked in this thread (and other threads on this site) about what's known re: low-level ANE capabilities, and it seems to have significant potential overall, even for some part of LLM processing. I'm not expecting it to be best-in-class at everything, though. Just like most other NPUs that are also showing up on recent laptop hardware.

Re: Apple M5 chip

#436

Post by wmf »

lostmsu wrote: post #315
jdlyga wrote: post #177

If only the Windows ecosystem could make the processor transition as smooth as Mac.

I don't think it is the ecosystem. The ARM CPUs not from Apple are just too slow.

X Elite and N1X are fine; the problem is with Windows.

Re: Apple M5 chip

#438

Post by mft_ »

yalogin wrote: post #200

It feels like apple is “ a square peg in a round hole” when it comes to AI - atleast for now. They are not the hardware provider like nvidia, they don’t do the software and services like OpenAI or even Microsoft/oracle. So they are struggling to find a foothold here. I am sure they are working on a lot of things but the only way to showcase them is through their phone which ironically enough feels like not the best p…

They are the leader in manufacturing consumer systems with sufficient high-bandwidth memory to enable decent-sized LLMs to be run locally with reasonable performance. If you want to run something that needs >=32GB of memory (which is frankly bottom-end for a somewhat capable LLM) they're your only widely-available choice (otherwise you've got the rare Strix Halo AI Max+ 395 chip, or you need multiple GPUs, or maybe a self-build based around a Threadripper.)

This might not be widely recognised, as the proportion of people wanting to run capable LLMs locally is likely a rounding error versus the people who use ChatGPT/Claude/Gemini regularly. It's also not something that Apple market on, as they can't monetize it. However, as time goes on and memory and compute power gradually decrease in price, and also maybe as local LLMs continue to increase in ability (?) it may become more and more relevant.

Re: Apple M5 chip

#439

Post by blihp »

condiment wrote: post #403
paxys wrote: post #392

M5 is 4-6x more powerful than M4, which was 5x more powerful than M3, which was 4x more powerful than M2, which was 4x more powerful than M1, which itself was 6x faster than an equivalent Intel processor. Great! Looking at my Macbook though, I can say with utmost certainty that it isn't 4000x faster than the Intel one I had 5 years ago. So, where is the disconnect here? Why is actual user experience not able to keep…

It's GPU performance. Spin up ollama and run some inference on your 5-year-old intel macbook. You won't see 4000x performance improvement (because performance is bottlenecked outside of the GPU), but you might be in the right order of magnitude.

Not possible given the anemic memory bandwidth [1]... you can scale up the compute all you want but if the memory doesn't scale up as well you're not going to see anywhere near those numbers.

[1] The memory bandwidth is fine for CPU workloads, but not for GPU / NN workloads.

Re: Apple M5 chip

#440

Post by semiinfinitely »

paxys wrote: post #392

M5 is 4-6x more powerful than M4, which was 5x more powerful than M3, which was 4x more powerful than M2, which was 4x more powerful than M1, which itself was 6x faster than an equivalent Intel processor. Great! Looking at my Macbook though, I can say with utmost certainty that it isn't 4000x faster than the Intel one I had 5 years ago. So, where is the disconnect here? Why is actual user experience not able to keep…

All those extra flops are spent computing light refraction in the liquid glass of the ui
Post reply on HN