alt Hacker NewsMacBook Pro with new M5 Pro and M5 Max
Comments
"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. Wondering if that will change with the overhaul of Siri this spring.
I love the following section of their copy:
> Even More Value for Upgraders
> The new 14- and 16-inch MacBook Pro with M5 Pro and M5 Max mark a major leap for pro users. There’s never been a better time for customers to upgrade from a previous generation of MacBook Pro with Apple silicon or an Intel-based Mac.
I read as "Whoops we made the M1 Macbook Pro too good, please upgrade!"
I think I will get another 2-5 years out my mine.
Apple: If you document the hardware enough for the Asahi team to deliver a polished Linux experiene, I'll buy one this year!
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 for the 128GB RAM 14” MacBook Pro model.
I feel like Apple pulled an Instant Pot with the M1 MacBook Pro. I still haven't had a single situation where I felt like spending more money would improve my experience. The battery is wearing out a bit, but it started out life with so much runtime that losing a few hours doesn't seem to matter.
The hardware looks amazing! Too bad they will ship with Tahoe installed. I’m not upgrading until I see in which direction the next Mac OS release goes
On M4 Max 128GB we're seeing ~100 tok/s generation on a 30B parameter model in our from scratch inference engine. Very curious what the "4x faster LLM prompt processing" translates to in practice. Smallish, local 30B-70B inference is genuinely usable territory for real dev workflows, not just demos. Will require staying plugged in though.
Whoah, both the Pro and Max CPUs feature 18 cores. This hasn't happened since M1 Pro/Max. This is a surprise.
Also, the mix of cores have changed drastically.
- 6 "Super cores"
- 12 "Performance cores"
I'm guessing these are just renamed performance and efficiency cores from previous generations.
This is a massive change from the M4 Max:
- 12 performance cores
- 4 efficiency cores
This seems like a downgrade (in core config but may not be in actual MT) assuming super = performance and performance = efficiency cores.
1.35x speed up in single core versus M3 Max. Insane. Everyone else has failed to bump single core performance in years. Where are these single core gains coming from?
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.
I have a fairly maxed out M2 Ultra (24 cores, 192GB RAM), and still cannot get this machine to choke on anything.
I have not once felt the need to upgrade in years, and that’s with doing pretty demanding 3D and LLM work.
Honest question. Is it possible to install an earlier version of macOS on these machines? Liquid glass looks so.. unprofessional to my eyes. And I hear it's also unstable.
"The new MacBook Pro gets up to 24 hours of battery life, giving Intel-based upgraders up to 13 additional hours"
I have a Intel-based 2019 Macbook Pro still and I have NEVER in its lifetime gotten even half of what they are claiming here. These days if I run it from battery I might get 90 mins.
That said I had a maxed out Macbook Pro M4 Max on order but just cancelled it right now and will get this new M5 Max one for basically the same price. Once I saw that they didn't up the price of memory (I don't know how it doesn't affect them) I canceled my order.
Interesting that they're showing VFX/CG software (Autodesk MAYA and Foundry Nuke) so prominently - obviously people using "Pro" machines are the target audience for this, but both of those apps (any many others in the industry) use Qt for the interface, rather than being totally platform-native.
$200 price bump across the board. The cheapest 16" is now $2699 and 14" Pro $2199. I think it's a fair price considering M2Pro 14" was $1999 (though it was discounted) only had 512GB and 16GB RAM.
One thing I haven't seen mentioned in this thread is M5 Pro now supporting 64GB ram . I believe prior gens you had to go Max to get 64. m5 Pro 64GB is $3000 meanwhile to upgrade ram on the max you need the 40 gpu core variant with 64GB is $4300. $1300 dollar mark up for twice the gpu compute and 50% higher mem bandwidth isn't great value imo.
I checked the fine print on the product website: by “up to 4x faster LLM prompt processing,” they’re specifically referring to time to first token. So it’s not about token generation rate (tokens per second).
Nano-texture is worth the upgrade if you are on a macbookpro whatever M<cpu> and dont have it.
For those of us with astigmatism it's really night and day experience.
Nice starting storage bump
MacBook Pro with M5 Pro now comes standard with 1TB of storage, while MacBook Pro with M5 Max now comes standard with 2TB. And the 14-inch MacBook Pro with M5 now comes standard with 1TB of storage.> M5 Pro supports up to 64GB of unified memory with up to 307GB/s of memory bandwidth, while M5 Max supports up to 128GB of unified memory with up to 614GB/s of memory bandwidth.
This is the important statement. 614GB/s is quite decent, however a NVIDIA RTX 5090 already offers 1,792 GB/s (roughly 3x) of memory bandwidth, for comparison.
Was hoping to see Apple break the 128GB barrier in a laptop that they previously set, though 128GB is still pretty sweet for local LLM inference on consumer hardware. My 128GB M3 Max is still shredding tokens pretty well (with that annoying slow initial prompt processing), so no major complaints there. I guess the question is, given access to the same amount of RAM, does the M5 really do an order-of-magnitude better than 128GB on a M3 or M4?
I don't see it mentioned much, but the most exciting thing to me is that they're shipping their own WiFi chip in it, which leads me to be hopeful that they'll eventually get around to shipping a cell modem so I don't have to tether to my phone constantly. Still no new colours unfortunately. I think those are the two things that would/will be exciting in the future. Give me a green 5g+ capable MBP and I'll be happy. I'm so deeply bored of the drab grey and darker grey versions; we can have tattoos at work now, give me a different colour laptop for christ's sake
So is this a minimal upgrade before the M6 Macbook Pros w/ OLED & a redesign later this year?
It doesn't even look like they added cellular as an option with their own C1X chip (getting around the licensing / cost issues since it's their own chip now).
Hot take - Local LLM computing will move to stationary, always on devices (Mac mini & studio). Developers and users will move to lighter, portable devices to interface with their long running agent workers (MacBook Airs & iPads).
Ugh, more "AI" hype. How useful are the cited hardware features for NON-"AI" processing?
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 mean the Ultra comes back in M6 since it would be easier to fab?
For those who don't already know, you can get a lot of PC gaming performance out of these machines using Sikarugir. You can install all of Steam via winetricks and go from there, or launch DRM-free games directly.
The question is when Apple Laptops are going to be able to run LLMs with a performance comparable to what the AI companies are offering?
I bought an M4 and don't think I can justify upgrading so soon. Certainly has some great improvements.
Does it still come with a measly 1 year warranty?
Shout out to LM Studio being featured in one of the product shots!
I just bought a M5 Macbook Pro 2 weeks ago. Thinking of returning it and getting a M5 Pro with the same configuration but only $200 more. How should I compare M5 vs M5 Pro?
It doesn't feel like much has changed from the previous gen? Just a new chip + memory?
I wonder how this compares to my M4 air with 10 GPU cores and 32 MB of RAM. My system can only run ~14B sized models at any reasonable speed. The accuracy of these sized models can be underwhelming. I am looking forward to a time when it would be nice to run models locally at a reasonable price, at a reasonable speed and with reasonable accuracy. I don't think we are there just yet.
I thought a Studio would be my local LLM machine 2026, but this is $2000+ for the 126gb option - not for me. I assume $6000 for that Studio machine but it looks now more like $8000.
I thought that new models were typically released in October. Have I misremembered or is this an unusual timing vs previous years? If so, I wonder why the earlier release?
I have an m4 pro MBP, 1tb storage and 24gb RAM. Not seeing any reason to consider an upgrade whatsoever.
My M3 Pro with 18gb of ram still feels like a beast. The only thing I can make it suffer with so far is generating meshes from 3D scanning, and even then I'm just patient. Apple is suffering from success with these older laptops, it's a tough sell to upgrade, even from the M1 Max folks.
An ”unrivaled experience” with MacOS Tahoe…
I have absolutely no need and yet I want ittttt
What's a good value for a used MacBook pro these days? Any of the older models worth buying today?
The screenshot of running LM Studio alongside Maya is a massive hardware flex.
Wish it was Blender though ;)
Considering these max out at 128GB of unified ram my guess is the hope of an M5 Ultra with 1TB of unified ram is unlikely to come true... Super disappointing.
Is the M5 Max the first laptop with significantly more memory bandwidth than the M1 Max? Looks like about a 20% jump… might finally be time to re-benchmark CFD workloads.
I'm done buying Macs until they prove they can ship an OS
I chased down what the "4x faster at AI tasks" was measuring:
> Testing conducted by Apple in January 2026 using preproduction 13-inch and 15-inch MacBook Air systems with Apple M5, 10-core CPU, 10-core GPU, 32GB of unified memory, and 4TB SSD, and production 13-inch and 15-inch MacBook Air systems with Apple M4, 10-core CPU, 10-core GPU, 32GB of unified memory, and 2TB SSD. Time to first token measured with an 8K-token prompt using a 14-billion parameter model with 4-bit quantization, and LM Studio 0.4.1 (Build 1). Performance tests are conducted using specific computer systems and reflect the approximate performance of MacBook Air.