I have to say, I really dislike the thing where the base M(n+1) is always in the market alongside M(n) Pro/Max. I appreciate the underlying chips are probably quite distinct, but from a naming standpoint its confusing as hell.
I'm guessing the Base and Pro chips come off the same wafer, and they get 5 Base chips (some defects) for every one Pro chip (very few defects). So they run the Base-model assembly line for six months and eventually they accumulate enough Pro chips to satisfy Pro-model demand.
makes me want to wait another one
I have an M1 Max and just set up playing with an M1 (non-max) and realized it can't drive 3 displays. I recall getting Max just for this, but generally, makes me think of non-Max as a non-pro after all.
And having what's presumably the latest CPU but with potentially worse features than the last generation combined with increased prices from RAM is a deal breaker so I'll guess I'll push my M1 for another year.
I get you, but I suspect it reflects reality. The M-with-adjective chips are M(n) chips with more cores and cache, it stands to reason that it takes real wall time for TSMC to start cranking them out with acceptable defect rates.
So Apple can either toss the early production in inventory while the whole process catches up, or they can do what they do. Better for both the company and the consumer that they do the latter.
I'm currently on a marathon to keep my M1 Pro running until the M7 Pro/Max is available. Not sure if I'll make it, but I'm not eager to pay $6000+ for a decent spec dev computer, until I really have to
I'm loving my M1 Macbook Air still, and only a few weeks away from six years of use Sometimes it lags a bit when I'm running a macOS VM, and all the coding agent VMs, so I'm kind of interested in going to 32GB of RAM, but honestly this computer is still faster than any of my laptops that came before, even with the visual atrocity of Liquid Glass.
I'll go and look at this new box, drool a little, and realize that I'd get more personal utility from donating $3k (or whatever the trade in delta is) to a charity than upgrading my computer.
My son's M1 Air CPU died suddenly. Maybe it was a thermal death from overheating. Not sure. But all the data on it was lost because the storage is soldered on. PSA to make sure devices with non-removable storage are backed up!
(We replaced it with a Framework... with removable storage.)
> PSA to make sure devices with non-removable storage are backed up!
Really this should be devices full stop. Also, "backed up" should include no fewer than two backups on different media and in different physical locations e.g. Time Machine to an external SSD _plus_ continuous cloud backup.
I bought my M1 Pro the week it came out and it was unlike any computer I ever had, expectations, compute, battery life especially. It was just a joy to use and not worry about chargers. I'm so glad they went this path.
I got a second hand M1 air like two years ago for 200usd with 1tb hdd and 16gb ram. I got it after my intel Air died after about..12 years? (Edit: the ssd died, which is removable… but literally had a plane to catch). All my pros have died within a few years. Air all the way. Never looking back.
The old airs were legendary. My 2012 still runs just fine despite being beaten to hell. Would still be a great dev machine for non-GPU workloads if it weren't for a lack of OS updates. Have been very happy with my M1 Pro as well though.
Just use. There were two models that had issues with the gpu desoldering, 2012 and 2015 iirc? I was lucky enough to have them. I put the mobos in the oven (180deg for seven minutes?) and that would fix it. For about a month… and then 2 weeks.. and then… I actually have a 2018 that I borrowed from a friend after my 2013 Air ssd gave up, it is still working I think, but its twice as slow, at least as my Air was. Its so weird. The Air stayed ‘snappy’ even after my friends Pro’s would become too sluggish. Maybe because I never update ;)
I wonder if this is from not trying to get maximum performance, and instead focusing on efficiency? But I've noticed this too. I definitely prefer the Air form factor over larger models as the primary benefit, but the durability seems to be a big benefit too. Fewer ports, thinner shell that seals tighter and can't flex as much due to the curved metal instead of flat surfaces... everything about it just seems like a better design.
No fans though. I like being able to crank them full blast. I'm not sure this pro would ever actually run the fans all out with my usage with the existing fan curve. Apple always favors it running quiet and hot, but I don't mind loud and prefer cool palms. I grew up with far more noisy rigs.
Been on HN for many years now, and the one thing that never changes is people posting angrily about small UI changes. It makes me wonder- if things have only ever gotten worse, what was the peak UI? MS DOS?
I think the biggest thing isn't really whatever it is but the act of changing and forcing everyone to change into the new ui that is the disruptive part. It is a combination of window dressing changing but also sometimes functions breaking. It is ironic because software written for developers prides itself generally on maintaining compatibility with say depreciated flags, or if things will be depreciated plenty of notice ahead of time. But that only holds for cli software. GUI software and the OS that all goes out the window. Stuff breaks, workflows break, you have no recourse and in fact they might make it genuinely difficult to go back to an older version. Like this part of it is the shitty part. Never mind how it happens to look. It is the forcing effect.
I think it’s also because these UI changes are always designed to improve first-impression and first-usage. They are outright hostile to anyone who wants to go fast and get faster — the power user. At minimum the re-arrangement resets any gains you had, and at maximum its irrecoverable because the UI is now fundamentally designed to slow you down.
This eventually becomes awkwardly precise complaints about information density and general change; but the underlying issue is I want to go fast and the system says no
I think the only real solution to this is to switch to an OS with a backing org that has optimization for power users as a first-class goal. I've been liking Omarchy and NixOS for that. I say this as a Mac user since 1989.
Leopard was better because it introduced spaces. Honestly I think that whole concept (I know windows has something analogous now) was the biggest step change in OS functionality I've seen in my life having started on windows 95.
Apple was actually last to the party on that. Linux had virtual desktops for years at that point, and Windows had them as well through Microsoft PowerToys. I’m pretty sure I was running it on Windows 2000.
Liquid Glass was not a "small UI change". It disrupted many accessibility aspects of macOS, so much so that Apple toned down quite a few aspects of the design in subsequent updates, even adding a slider to reduce the effect. [1]
The quantity of requests for how to disable Liquid Glass on Apple Discussions is staggering. [2]
Small improvements don't get much accolades. And for the most part, the UX is so good that most changes tend to be neutral or for the worse. And when you're really attached to something and there's on an unnecessary change, it feels almost like betrayal!
I, for one, prefer Apple products because they sweat the small stuff more than the other options, and when they have put in effort to make things worse it's kind of infuriating.
I do a bit of desktop Linux work too, and it's OK, but hard to complain when it's all open source volunteer work! Windows is so terrible that I wouldn't even know where to start. What's the point? There's nobody at Microsoft that even gives a damn.
The way things are going you will be able to run your favorite flavor of Linux on those pretty soon.
It will be the best of both worlds: the best hardware and a good OS. Hopefully Apple doesn't take steps to block it.
Liquid Glass is more than just the transparency. There are many other changes that cannot be disabled that way. Not to mention the overall lag compared to Sequoia (I skipped Tahoe entirely so I had a direct knife-edge transition). 27 is less bad than 26 but Liquid Glass doesn't make anything better than prior UI and makes several things worse, even if you turn down the transparency.
I imagine that the UI changes since Sequoia regarding the giant buttons and whitespace are because Apple plans to release a touchscreen laptop (most rumors say it will be announced tomorrow) so they've decided to make the UI touch friendly at the expense of bloating the UI for everyone who doesn't have a touchscreen. Microsoft made this same decision with the Windows releases after 7.
Stay strong! I went from an M1 to M5 generation, and it was a nice bump, but I could have gone another year without any significant impact on my quality of life/work.
I've been using my M1 Max 64 GB for 5 years now and it's pretty zippy once you rewrite some slow software. I have an M4 Max with 128 GB but I never ended up migrating to it. That's how good it is.
I think I'm on the same computer, the M1 MBP with the touchbar right? I was eyeing an upgrade for a while but now that I've transitioned to running agents on a home server instead of locally, I think I'll be putting my money into a ram upgrade for that box instead. My macbook is basically a dumb terminal at this point, the only reason for an upgrade would be battery life. I might get an air or even a neo if this thing dies.
I’ve been a Mac user for 20 years and it’s wild to think how slow my 2003 PowerBook G4 or even my 2008 MacBook Pro felt after five years compared with my 2021 M1 Pro.
My 2013 Core i7 took almost eight years to get to where the previous ones were at five, and if it weren’t for local LLMs pushing me toward an upgrade in the next year or two, I have to imagine my M1 Pro could be my daily driver well into the next decade.
Have an M1 air as well. Got a Pro m5. For daily coding tasks, and general web browsing the M1 air still holds. I'm going to pass it on to my kid. Reminds me of the honda we have that we'll also pass down.
Biggest issue with my M3 Max is apple mandatory fun bloatware. I think it's the same playbook as phones long term. The hardware is still powerful but the software is optimized for the latest CPU, so older models run hot, take a fraction of the second longer to load the resources, etc. That stacks up over 5-6 years of releases to make older models feel slower.
I had an M1 Max machine with 32GB of memory and upgraded it to an M4 Max machine with 128GB of memory for local AI model experimentation.
It's sad that M5 (and M6) are so much faster at prefilling and other LLM-related operations, but I'm happy with the computer I got and will keep it at least 3-4 generations.
They really have radically improved the situation for prefill speed! But the generation speed is behind enough that you'd notice. An M4 Max is a great choice I think.
I have an M1 Pro as well but my next computer will be a split setup mainly because I realized that I'm most often working / focusing on hard things while at the desk and just browsing / checking in on things when I'm away from the desk so I'm thinking something like:
that's the plan for now, I just haven't had the M1 Pro slow down/hang/lag enough to give it up. It's a mid-range M1 Pro with 32GB of ram, works for me for dev work, I don't run any local LLM or resource intensive things on it. Battery only has 250 cycles on it so it's not like it dies off-charger.
I have M1 Maxes (one for work, one for home) that perform as good as new, as far as I can tell. Only thing they lack is an Nvidia GPU. I might pick up the new uber-studio though tmw when it launches (presumably).
I just bought a m1 Air with 8GB as secondary device to the m4 mbp that my employer provides since they dialed up the spyware lately.
I should have bought a m4 Air last November but I hope the m1 holdes until the rampocalypse is over.
How useful would that actually be for local inference, when the bottleneck is, essentially, always memory size? I think the sweet spot is somewhere around 64 to 128 GB. That ought to be enough for almost all uses, like Qwen3.8-Flash-Next at a decent quant.
Memory size is a bottleneck, but I have found that speed is very important for getting actual work done. Running a big model is great, but if you're getting 10t/s you're going to be spending a lot of time waiting.
I thought we were supposed to get a design overhaul this gen?
Also framing AI use for the base M models marketing makes no sense to me. You are way better off getting a used M1 max with 64gb and way higher mem bandwidth when those are the real bottlenecks.
Apparently another announcement coming tomorrow, with the OLED panels. But according to the fpt channel on Youtube, it doesn't look any different. Just has an OLED panel with touchscreen, with massive cooling changes inside.
I switched entirely over to Asahi Linux on my M1 Macbook Air and installed a third-party 55Wh battery, as the original battery had fallen below 80% capacity. That machine is good to go for another 5 years.
There are no features or performance characteristics of any of the subsequent M[2-6] Macbook Air or Pro models that I care about. I'm not really sold on running models on the hardware I have right in front of me. So long as I can rent an RTX PRO 4000 Blackwell at about half a buck per hour through a European provider, I'm fine using that with Qwen3.8-27B UD-Q4_K_M for the few things I consider more privacy-sensitive.
How is Asahi Linux from a reliability perspective? Last I checked there were some issues with docking and HDMI out that would've made it tough for me to use as a daily driver.
I have been a fan of these newer macbooks. They are just pushing the boundaries of a good laptop. While I understand the use, I hope someday my AAA games are also as supported in MacBooks as my gaming laptop.
I'm generally with you on it, they're sort of fatiguing in a depressing way.
But try the new James Bond game. Linear shooter, but a great story and fantastic cast on top of super fun mechanics. By the Hitman studio with a lot of their core ideas Bondified to favor action over stealth. It hasn't irritated me in the way almost any other game manages to.
Depends on the game obviously. e.g. Assassin's Creed N+1 - you've seen the formula like 20+ times already, all the previous games + all of Far Cry from 3 upwards. There's nothing new. And there's Cyberpunk2077 and BG3 which are still huge but unique and carefully designed
The decompilation efforts I've been seeing with 15 year old Xbox 360 games or PS3 games has been absolutely incredible, getting them running natively on macOS with presumably much fewer engineering resources than are allocated to a standard game port.
I do think the limited macOS gaming market is a chicken-or-the-egg problem - people don't game on Macs because there aren't that many great games on Mac (Although Cyberpunk runs amazingly on my M4 Macbook Pro).
> I do think the limited macOS gaming market is a chicken-or-the-egg problem
This feels like a re-hash of Valve's original Steam Machine mistake. Porting modern games to native Linux didn't increase user or developer interest in supporting the platform. It made Valve liable for a lot of investment into systems that no developers ever used, and Valve themselves would eventually abandon.
Apple has stepped in this same cowpie. They depreciated hundreds of "old" macOS games by radically changing their runtime, and then nobody invested into the new Metal-native paradigm. Porting games like Tomb Raider and Death Stranding won't kickstart the macOS gaming revolution any more than native Left 4 Dead magically made Linux an alternative to Windows for gaming. We know this from experience.
Decomps and emulation is a good solution for 15-year-old games, but Apple can't enjoy day-1 support if they refuse the industry's standards. There is no trust in Metal as a stable API, or macOS as a reliable and backwards-compatible runtime. Windows is not only much more profitable, it's easier to support for decades to-come.
That's exactly what I am doing. I have a Dell R740 with 96 cores and 512 GB of RAM, and RAID 10 with 16 SSDs. All of my machines connect to it via Tailscale.
Just now realizing there's a difference between "MacBook Pro with M# chip" and "MacBook Pro with M# Pro chip". Was curious to see how my MBP with M4 Pro compared, and I saw it has 273 gb/s memory bandwidth compared to the MBP M6 (sans Pro)'s 170gb/s. Makes sense that "Pro" in the laptop model doesn't also describe the chip, but only if you remember that the non-pro "Macbook" line stopped in 2017 (which was the last time I went shopping for Apple laptops until buying the MBP4)
Am I crazy, or are a lot more people using the term "uplift" in place of "increase" within the last year? Google Trends (for whatever it's worth) shows a significant increase (uplift?) since mid-late 2025. [0]
Language changes. People at work have started saying things are an easy lift instead of a quick win. And it's not new hires, it's the people I've worked with for years. I never got on board with quick win either.
Some people adopt stuff faster than others. I've lived in NZ for nearly 20 years and called someone bro for the first time just last week while playing a sport "should have left it for me bro". Slipped out natural as. Still having bad thoughts about it.
If you want to do anything beyond getting a small single-core speed bump the M5 Pro is a better, more capable purchase. At least until the M7 comes out.
The M6 version is also cheaper than the M5 Max by a significant amount. I wouldn't be surprised if the M6 could keep up on LLM prefill (compute bound), but the memory bandwidth means that decode is going to be a lot slower, most likely?
It's a base M6 chip. The Pro doubles that, and the Max doubles again. And the Ultra doubles yet again. This is how the entire M series has always worked.
It's also absolutely wild that you apparently cannot spec one with more than 32GB, for any amount of money? Wow.
Not that I blame Apple here, for once. Seems like they're trying to cope with the limited quantity of RAM they can procure. And with the paltry bandwidth (170GB/s) of these CPUs they're a bad choice for anything but tiny local models anyway.
That's for the base model M6. The Pro can take more, the Max even more, the Ultra the most.
They're not making those models for the M6 though; they rerouted their resources to making M7 faster at running local LLMs.
If you want more bandwidth, get an M5 Pro, Max, or Ultra. If you want a lower power base model, get the M6. If you want to have your cake and eat it too, wait for the M7, reportedly in the spring.
Hmm, still no OLED displays? I wonder what's the holdup? (I have a fairly mainstream PC laptop with OLED display, and the display is the one thing where my MBP looks pretty poor in direct comparison).
The design is really great for the new MacBook Pro. The cpu is no compare to other laptops.
One thing, framing AI use for the base M models marketing makes no sense to me.
But honestly this computer is still faster than any of my laptops that came before, even with the visual atrocity of Liquid Glass.
Still using my 8gig m1 to make mac builds, its slow, but works fine. Keep thinking about upgrading, but max 32gigs ram, if I can hold out for 2 years, and maybe have 64/128gig as options, and cheaper.
As lots of Apple Users are in here: I'm thinking about "sidegrading", my M2 Pro runs fine, but I chose 16 GB/512 GB when I bought it and I think 32 GB/1 TB would be nicer in some cases.
Is it easily possible to sidegrade/upgrade with a Timemachine backup?
Is this an odd rollout for their actual high end MacBook Pros, or is this sitting in that space where they like to have a base MacBook Pro between their Airs and the expensive MacBook Extremely Pros?
Just the standard chip without Pro/Max makes me assume this is that base one. If so, the price is way high for where that tends to sit, but welcome to buying a computer in 2026 I guess.
This is the base one. You get a better display, more, faster Thunderbolt ports, and an honest to god HDMI port, plus some fans for cooling on long running processes that you don't get with the M6 Air (which also doesn't exist).
I think it makes sense. Do you think most potential buyers are coming from last year's model, or from laptops that are more like 3-5 years old?
As long as they're clear about the comparisons they're making ("X% more battery life than Y" as opposed to simply ("X% more battery life") I'm good with it.
There's no happy medium here that would satisfy everybody: when they make marketing claims about improvements relative to products from several years ago, they get criticized for not focusing on the improvements relative to last gen (even if those comparisons are also somewhere in the announcement). When they focus on the most recent generations, people complain that it doesn't make sense to upgrade every year.
Just accept that even if you aren't still using an Intel MacBook Pro, the comparison is still relevant to some part of their target market.
They only just dropped support for Intel Macs from this fall's operating system release (but are still doing security patches for the releases that Intel Macs can run). A year from now, it actually will be fairly reasonable to expect them to give up marketing to the holdouts.
I would guess there's still quite a lot of people on Intel Macs out there (they were sold 5 years ago), so it is still very much worth it for Apple to market to them.
Why? Apple devices have the best battery life in the market right now to my knowledge. It's an important part of the evaluation for a laptop which is the opposite of cringe.
Actually, they don’t! Intel Core Ultra Series 3 beats Apple laptops as of the M5 on battery life.
IIRC the Framework 13 Pro beats the MacBook Pro at both video streaming tests and office productivity with 300 bits brightness tests. (Framework live-streamed the video playback test, and the office provided productivity tests I referred to were done by Just Josh Tech)
Perhaps the M6 has leapfrogged but that remains to be seen.
In usual developer type tasks, among my friend group what I hear is that panther lake laptops are competitive with M4 laptops. But, M4s do that with a 55Wh battery, whereas most panther lake laptops come with a 70Wh battery. So if you're discussing chip performance per watt then it's probably an edge to apple silicon.
I recall seeing some crazy stats like 41+ hours maybe on a snapdragon processor w/windows. I imagine your screen brightness would have to be like 99% dark and not playing videos is my guess.
Why would you want greasy fingerprints all over your display and gorilla arm syndrome when there's a perfectly fine keyboard and touchpad attached to the display for free?
No reason for gorilla-arm when touch is an alternative interaction mode and not a required one. You still have trackpad and keyboard. You can dynamically switch modes depending on the action.
Gorilla-arm was a fear based on the naive idea that if you had touch, you would be required to only use touch for every action.
Is apple going to be so restrained to keep the design of the OS as a mouse first experience or are they going to cripple information density so I might be able to close a window with my elbow?
One of the interesting slights of hand Apple marketing must do is simultaneously say the new processor is awesome while selling the higher spec versions of the previous processor as upgrades:
The M6 chip joins M5 Pro and M5 Max to create our most advanced line-up of chips ever built for a pro laptop. With a 12-core CPU, 12-core GPU and our first ever Dual 16‑core Neural Engine, M6 brings next-generation speed and advanced on device AI. All three chips deliver phenomenal single- and multithreaded CPU performance and faster unified memory. . . .
The case of your 5090 having become a coveted artifact of great rarity in these times - may be a nuance of some measure.
Also, the following two have very different 'needs' to feel good enough:
1. heavy agentic workloads via harness
vs
2. a simple private chat interface with a local instance
Even if an MBP's bandwidth were higher, it's tough to see a reason to run it as a constantly loaded 24/7 inference machine due to heat degradation.
P.S. still extremely awesome to be able to host and chat with a decently quantized 27B model on your laptop. ...and to be fair even a 32GB Air would do that!
It is a thing of beauty: the amount of folks this may add to the hacker/tinker community.
The 5090 does have a bandwidth advantage, but also must pass more data from main to GPU memory for any particular task. Comparisons of a 5090 to a DGX Spark at 273 GB/s are illustrative since the Spark uses unified memory similar to Apple's M-series. [0] The 5090 certainly wins most benchmarks but that doesn't mean the DGX Spark is not useful.
About time they put a battery in the lid, which is what an iPad already manages to do with thinness. Boom another half a decade of updates all the way to 48hrs
It's confusingly worded but I think it's a suggestion for something Apple could do in the future. I don't see any mention of this in the linked Apple article.
I'm currently having an M2, but I just can't imagine buying an Apple laptop again. The hardware is great, but the sofware is just unbearably bad. I used Arch Linux with KDE before, and it was just an experience 10 times better. If they would just support Linux out of the box...
makes me want to wait another one I have an M1 Max and just set up playing with an M1 (non-max) and realized it can't drive 3 displays. I recall getting Max just for this, but generally, makes me think of non-Max as a non-pro after all.
And having what's presumably the latest CPU but with potentially worse features than the last generation combined with increased prices from RAM is a deal breaker so I'll guess I'll push my M1 for another year.
So Apple can either toss the early production in inventory while the whole process catches up, or they can do what they do. Better for both the company and the consumer that they do the latter.
I'll go and look at this new box, drool a little, and realize that I'd get more personal utility from donating $3k (or whatever the trade in delta is) to a charity than upgrading my computer.
(We replaced it with a Framework... with removable storage.)
Really this should be devices full stop. Also, "backed up" should include no fewer than two backups on different media and in different physical locations e.g. Time Machine to an external SSD _plus_ continuous cloud backup.
> We replaced it with a Framework... with removable storage.
Cool. How are you backing it up?
The battery doesn't hold a charge anymore, but as long as it's plugged in, it keeps chugging along.
What are you doing to them?
I still have MBPs from 2015 and 2018 that have not 'died'.
This eventually becomes awkwardly precise complaints about information density and general change; but the underlying issue is I want to go fast and the system says no
Apple was actually last to the party on that. Linux had virtual desktops for years at that point, and Windows had them as well through Microsoft PowerToys. I’m pretty sure I was running it on Windows 2000.
The quantity of requests for how to disable Liquid Glass on Apple Discussions is staggering. [2]
[1]https://www.macrumors.com/2026/06/09/macos-golden-gate-liqui...
[2]https://discussions.apple.com/thread/256227663
I, for one, prefer Apple products because they sweat the small stuff more than the other options, and when they have put in effort to make things worse it's kind of infuriating.
I do a bit of desktop Linux work too, and it's OK, but hard to complain when it's all open source volunteer work! Windows is so terrible that I wouldn't even know where to start. What's the point? There's nobody at Microsoft that even gives a damn.
Um. https://imgur.com/a/ydt3MN5
My 2013 Core i7 took almost eight years to get to where the previous ones were at five, and if it weren’t for local LLMs pushing me toward an upgrade in the next year or two, I have to imagine my M1 Pro could be my daily driver well into the next decade.
But with all of the AI-discovered exploits I think it'll become more important to keep everything up to date
It's sad that M5 (and M6) are so much faster at prefilling and other LLM-related operations, but I'm happy with the computer I got and will keep it at least 3-4 generations.
- a low end Macbook Pro or Air
- Mac Studio, mid-to-high specs
This will be the “640kb ought to be enough for anybody” Bill Gates quote of our era.
Also framing AI use for the base M models marketing makes no sense to me. You are way better off getting a used M1 max with 64gb and way higher mem bandwidth when those are the real bottlenecks.
There are no features or performance characteristics of any of the subsequent M[2-6] Macbook Air or Pro models that I care about. I'm not really sold on running models on the hardware I have right in front of me. So long as I can rent an RTX PRO 4000 Blackwell at about half a buck per hour through a European provider, I'm fine using that with Qwen3.8-27B UD-Q4_K_M for the few things I consider more privacy-sensitive.
But try the new James Bond game. Linear shooter, but a great story and fantastic cast on top of super fun mechanics. By the Hitman studio with a lot of their core ideas Bondified to favor action over stealth. It hasn't irritated me in the way almost any other game manages to.
I do think the limited macOS gaming market is a chicken-or-the-egg problem - people don't game on Macs because there aren't that many great games on Mac (Although Cyberpunk runs amazingly on my M4 Macbook Pro).
I'm very excited for the future.
This feels like a re-hash of Valve's original Steam Machine mistake. Porting modern games to native Linux didn't increase user or developer interest in supporting the platform. It made Valve liable for a lot of investment into systems that no developers ever used, and Valve themselves would eventually abandon.
Apple has stepped in this same cowpie. They depreciated hundreds of "old" macOS games by radically changing their runtime, and then nobody invested into the new Metal-native paradigm. Porting games like Tomb Raider and Death Stranding won't kickstart the macOS gaming revolution any more than native Left 4 Dead magically made Linux an alternative to Windows for gaming. We know this from experience.
Decomps and emulation is a good solution for 15-year-old games, but Apple can't enjoy day-1 support if they refuse the industry's standards. There is no trust in Metal as a stable API, or macOS as a reliable and backwards-compatible runtime. Windows is not only much more profitable, it's easier to support for decades to-come.
"windows is the most stable ABI"
I think my 48GB 16 inch MBP will last me 15+ years at this point.
https://www.apple.com/mac/compare/?modelList=MacBook-Neo-A18...
Apple MacBook M5 Max has bandwidth up to 600GB/s, is 170GB/s for M6 the real limit? If so, wouldn't this slow down LLM processing?
Even then, 170GB/s is a bump up from 153GB/s of the M5. So we see a 11% uplift already.
Am I crazy, or are a lot more people using the term "uplift" in place of "increase" within the last year? Google Trends (for whatever it's worth) shows a significant increase (uplift?) since mid-late 2025. [0]
[0] https://trends.google.com/explore?q=uplift&date=today%205-y&...
See also: The use of "learnings" instead of "lessons."
Some people adopt stuff faster than others. I've lived in NZ for nearly 20 years and called someone bro for the first time just last week while playing a sport "should have left it for me bro". Slipped out natural as. Still having bad thoughts about it.
My M2 Pro does 200GB/s.
wtf are we even talking about here.
What was the speed of the base M5?
So the theoretical Max would be 680GB/s.
Not that I blame Apple here, for once. Seems like they're trying to cope with the limited quantity of RAM they can procure. And with the paltry bandwidth (170GB/s) of these CPUs they're a bad choice for anything but tiny local models anyway.
They're not making those models for the M6 though; they rerouted their resources to making M7 faster at running local LLMs.
If you want more bandwidth, get an M5 Pro, Max, or Ultra. If you want a lower power base model, get the M6. If you want to have your cake and eat it too, wait for the M7, reportedly in the spring.
One thing, framing AI use for the base M models marketing makes no sense to me. But honestly this computer is still faster than any of my laptops that came before, even with the visual atrocity of Liquid Glass.
Is it easily possible to sidegrade/upgrade with a Timemachine backup?
Then do a fresh install on your new system and then use Migration Assistant. Use a USB-4 or a Thunderbolt cable to speed it up.
Just the standard chip without Pro/Max makes me assume this is that base one. If so, the price is way high for where that tends to sit, but welcome to buying a computer in 2026 I guess.
It's the same rollout they've used for a couple of generations now. First the base model chips in fall, then the pro/max versions in spring
the m2/m3 announcements were already kind of cringe to keep saying 'HEY IT'S BETTER THAN INTEL' but at this point it's just embarrassing?
So Apple is now comparing against computers they were selling 7-8 years ago rather than what Intel is delivering now.
Source for that fun fact?
Apple didn't fully stop selling Intel macs until June 2023. And they compare against the most recent previous model too.
As long as they're clear about the comparisons they're making ("X% more battery life than Y" as opposed to simply ("X% more battery life") I'm good with it.
Just accept that even if you aren't still using an Intel MacBook Pro, the comparison is still relevant to some part of their target market.
They only just dropped support for Intel Macs from this fall's operating system release (but are still doing security patches for the releases that Intel Macs can run). A year from now, it actually will be fairly reasonable to expect them to give up marketing to the holdouts.
probably because of its adjacency to "corpulent" lol
> Mrs. Krabappel: "Embiggens"? I never heard that word before I moved to Springfield.
> Ms. Hoover: I don't know why. It's a perfectly cromulent word.
But now it has made it into the Merriam-Webster dictionary.
IIRC the Framework 13 Pro beats the MacBook Pro at both video streaming tests and office productivity with 300 bits brightness tests. (Framework live-streamed the video playback test, and the office provided productivity tests I referred to were done by Just Josh Tech)
Perhaps the M6 has leapfrogged but that remains to be seen.
Intel and now Qualcomm are really not far off on performance per watt. Mostly Apple maintains an advantage on single core performance.
The Panther Lake integrated GPU in the X7/X9 SKI is actually faster than the one you get in the base M5.
Gorilla-arm was a fear based on the naive idea that if you had touch, you would be required to only use touch for every action.
The fastest M6 MacBook Pro (24/32GB configs) has a memory bandwidth of 170 GB/s. And the M5 Max is 614 GB/s.
Am I missing some nuance of the M6 MBP here, or am I right to assume it won't set the local LLM world on fire?
Also, the following two have very different 'needs' to feel good enough:
1. heavy agentic workloads via harness vs 2. a simple private chat interface with a local instance
Even if an MBP's bandwidth were higher, it's tough to see a reason to run it as a constantly loaded 24/7 inference machine due to heat degradation.
P.S. still extremely awesome to be able to host and chat with a decently quantized 27B model on your laptop. ...and to be fair even a 32GB Air would do that! It is a thing of beauty: the amount of folks this may add to the hacker/tinker community.
0. https://float16.cloud/en-en/ai-benchmark/dgx-spark-vs-rtx-50...
M5 Max (128gb) is 600gb/s
Rtx spark laptop (128gb) is 200gb/s.
Desktop 5090 (32gb) is 1700gb/s.
Desktop 6000 (96gb) is 1700gb/s and 600W.
So, yes?