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

MacBook Pro with M5 Pro and M5 Max

apple.com

Post reply on HN
Print view View original

371–380 of 1001 posts

Re: MacBook Pro with M5 Pro and M5 Max

#371

Post by throwforfeds »

spiderice wrote: post #342
throwforfeds wrote: post #248

Earlier quoted context omitted.

Love that they didn't learn anything from the touchbar.

Comparing the touchbar to a touch screen is silly

I guess I'm just a luddite that spends my life on a CLI or text editor. Taking my hands away from my keyboard to leave finger prints on my screen just doesn't make sense to me.

I think people that do do tasks where a touch screen makes sense are probably just doing most of their work on an iphone or an ipad anyway.

Now gesture control on VR/AR setups? Sure, that feels like a new human/computer interaction system that makes sense. Jabbing at my laptop screen with one hand on my keyboard, not so much.

Re: MacBook Pro with M5 Pro and M5 Max

#372

Post by pwython »

rapfaria wrote: post #239
pwython wrote: post #118

Well that's. Just. Great. I bought a 64GB M4 Max MBP last month. I'm past the 14-day return window. I figured the M5 was near, but assumed M5 Max would come a bit later. Not sure where I came up with that.

Not sure either since M5 base has been available for months now

Ah yes, that's right. I was looking at the M5 model last month wondering why there was no 64GB option.

Re: MacBook Pro with M5 Pro and M5 Max

#373

Post by sgt »

jsheard wrote: post #31
wincy wrote: post #12

I typed “RAM” to search for it and boy they hammer home how lucky I am to be getting 1TB SSD standard, but no mention of RAM anywhere on this page. Anyway, the MacBook Pro starts with 16GB of RAM. It’s $400 to go from 16GB to 32GB. Interestingly, 36-128GB models are showing as “currently unavailable” on the store page, and you can’t even place an order for them right now? But for anyone curious, it’s quoting $5099 fo…

> It’s $400 to go from 16GB to 32GB. No change from the previous models then, 16GB->32GB was already $400. They're cutting into their previously enormous margins to keep the prices stable, rather than hiking the prices to maintain their margins.

In practice, you can really go a long way on 16GB on a Mac with unified memory. I like to say it's comparable to 32GB during the old Intel days.

Re: MacBook Pro with M5 Pro and M5 Max

#374

Post by nozzlegear »

qudat wrote: post #346
wincy wrote: post #310

Earlier quoted context omitted.

It’s a losing battle me trying to tell my wife to close her Firefox tabs, haha, but yes, Firefox does use a lot of ram when you have 500 tabs. Maybe I’ll get her a 64GB MacBook Pro for the premium web browsing experience she so desires!

Tabs as bookmarks, people keep falling into this trap, my wife included

I do it myself and I'm sure a lot of people on HN do too. But I've tried to embrace the "zen" of closing all tabs lately and it's been nice. If I really want to find something later I can search my history or, like you said, just bookmark it.

Re: MacBook Pro with M5 Pro and M5 Max

#375

Post by matthewfcarlson »

neya wrote: post #192
Tangokat wrote: post #5

"Scaling up performance from M5 and offering the same breakthrough GPU architecture with a Neural Accelerator in each core, M5 Pro and M5 Max deliver up to 4x faster LLM prompt processing than M4 Pro and M4 Max, and up to 8x AI image generation than M1 Pro and M1 Max." Are they doubling down on local LLMs then? I still think Apple has a huge opportunity in privacy first LLMs but so far I'm not seeing much execution.…

> I still think Apple has a huge opportunity in privacy first LLMs This correlation of Apple and privacy needs to rest. They have consistently proven to be otherwise - despite heavily marketing themselves as "privacy-first" https://www.theguardian.com/technology/2019/jul/26/apple-con...

I think it's all about relativity. Are they private compared to an open source privacy focused OS like grapheneOS and the fantastic folks running that project? No. Are they more private than a company like meta or google who has much worse incentives for privacy than Apple? Probably.

Do I wish Apple was way more transparent and gave users more control over gatekeeper and other controversial features that erode privacy? Absolutely.

Re: MacBook Pro with M5 Pro and M5 Max

#376

Post by GeekyBear »

The most interesting change for the M5 Pro and Max is Apple moving to a bonded chiplet strategy from a single monolithic die.

> The tech giant says the chips are engineered around its new Fusion Architecture, an advanced design that merges two dies into a single, high-performance system on a chip (SoC), which includes a powerful CPU, scalable GPU, Media Engine, unified memory controller, Neural Engine, and Thunderbolt 5 capabilities.

https://techcrunch.com/2026/03/03/apple-unveils-m5-pro-and-m...

They also replaced the efficiency cores on the CPU chiplet with a new higher performance design.

> The CPU now features six “super cores,” which is Apple’s term for its highest-performance cores, alongside 12 all-new performance cores. Collectively, the CPU boosts performance by up to 30% for pro workloads.

Re: MacBook Pro with M5 Pro and M5 Max

#377

Post by manmal »

andy_ppp wrote: post #69
Tangokat wrote: post #5

"Scaling up performance from M5 and offering the same breakthrough GPU architecture with a Neural Accelerator in each core, M5 Pro and M5 Max deliver up to 4x faster LLM prompt processing than M4 Pro and M4 Max, and up to 8x AI image generation than M1 Pro and M1 Max." Are they doubling down on local LLMs then? I still think Apple has a huge opportunity in privacy first LLMs but so far I'm not seeing much execution.…

It is simply marketing nonsense - what they really mean (I think) is they support matrix multiplication (matmul) at the hardware level which given AI is mostly matrix multiplications you'll get much faster inference (and some increase in training too) on this new hardware. I'm looking forward to seeing how fast a local 96gb+ LLM is on the M5 Max with 128gb of RAM.

We've already established in this thread that memory bandwidth isn't that much greater than M4 Max - 12%? However, I wonder if batched inference will benefit greatly from the vastly improved compute. My guess is that parallel usage of the same model will be a couple times faster. So, single "threaded" use not that much better, but say you want to run a lot of batch jobs, it'd be way faster?

Re: MacBook Pro with M5 Pro and M5 Max

#378

Post by bombcar »

NetMageSCW wrote: post #237
aurareturn wrote: post #208

Earlier quoted context omitted.

Interesting. This is clearly a big CPU change if so. I wonder why no E cores. I’m sure E cores would be more efficient at OS tasks than the new performance cores. For example, 6 super, 8 performance, and 4 efficiency.

Another commenter stated the P cores can be scaled down to be E cores dynamically, so why not?

I wonder if they'll get to good enough scaling from E to Super where they don't really need to distinguish anymore?

Re: MacBook Pro with M5 Pro and M5 Max

#379

Post by pram »

fooblaster wrote: post #201
kamranjon wrote: post #101

Earlier quoted context omitted.

I'm not sure if you're just unaware or purposefully dense. It's absolutely possible to get those numbers for certain models in a m4 max and it's averaged over many tokens, I was just getting 127tok/s for 700 token response on a 24b MoE model yesterday. I tend to use Qwen 3 Coder Next the most which is closer to 65 or 70 tok/s, but absolutely usable for dev work. I think the truth is somewhere in the middle, many peop…

what inference runtime are you using? You mentioned mlx but I didn't think anyone was using that for local llms

LM Studio has had an MLX engine and models since 2024.

Re: MacBook Pro with M5 Pro and M5 Max

#380

Post by wmf »

MBCook wrote: post #257

Can someone comment on the new dual die thing they’re promoting for how they make the M5 Pro and M5 Max chips? How is that different from the silicon interposer they were using before? The big change is the two dies don’t have to fabbed next to each other in a single wafer, which is fantastic for costs and yields. But would this affect the interconnect speed somehow? How would the two be wired together? Could this me…

the new dual die thing they’re promoting for how they make the M5 Pro and M5 Max chips?

It's chiplets just like GB10, Strix Halo, etc. One die has the CPU and the other die has the GPU.

How is that different from the silicon [bridge] they were using before?

It's probably similar.

the two dies don’t have to fabbed next to each other

They never were; this is a widespread misunderstanding.

But would this affect the interconnect speed somehow?

Apple never documented the internal interconnect for the M4 Pro/Max and now they don't document it for the M5 Pro/Max so we don't know. It's probably better to read reviews and avoid theorycrafting and backseat driving.

Post reply on HN