I find that hard to believe at Apple. Not even possible that it’s accidental. They have their own internal tools, all packets leaving the network will be interrogated, leaking data is a sackable offence… if it’s in the geekbench database then it’s there because they put it there.
No I think Apple employees run geekbench for fun and don't care the stats get uploaded (you know just like other normal careless humans rather than demigods)
Just recently there was the OpenAI vs Apple trial, where it came out that employees that left the company still had access to their internal net, sooo super plausible
I noticed a whiff of panic at the iphone 18 launch. Opened macrumors and there like 6 articles in a row about preordering the phone, how soon you can get the phone when you preorder, how long the queues are etc.
Guess they didn't get the expected # of preorders.
I'm currently in the middle of porting a game from 2004 to run on MacOS via wine. On a 5000$ Macbook Pro, I'm getting about 4 FPS. This has multiple causes, including the game being single threaded and running through Rosetta, but damn is it hard to get good single core performance out of Macbooks.
Out of curiosity, I also ported the game to arm Linux with fex + upstreamed the wine patches in about a third the time and there's no FPS issues
What porting you talking about exactly? Packaging existing binaries? Compiling source code making it more compatible with Wine?
In my experience as game developer and porting C++ code tells such difference usually mean there are something really wrong with syncronization primitives. So 99.99% of the time code does nothing just waiting for something to unlock.
Running something with "Wine" doesn't usually mean "porting", "porting" means making a native binary that doesn't run through an emulation layer.
Anyway, probably you are trying to run a 32-bit executable with Rosetta, that won't be fast, because Rosetta was never meant to run 32-bit things and has got a lot of pitfalls.
I recommend you try giving your AI an open ended task like, "it's at 4 fps even though it's a 22 year old game and the raw hardware performance is many orders of magnitude higher. Maybe due to running under Wine and Rosetta. Please figure out the simplest way you can unlock usable performance (30-60 FPS) short of decompiling, reverse engineering, and reimplementing the full game yourself natively. Maybe there is something else you can figure out for the performance unlock. The hardware is definitely there, so there has to be a way. The game is running so make sure you don't break it. Keep the same game behavior."
Regardless of which AI you're using, it will be able to figure something out in a few hours. 2004 pc's were 500-800 mhz, 128 MB RAM, and if they had a GPU at all it was 16-32 MB, 0.2-1 GLOP.
Your AI should be able to figure out a way to get it running in realtime.
Something is going horribly wrong. I don't know what it is (without your code I don't know), have you profiled where it's going wrong? There's no way a game for 2004 would be that slow.
If you want help, I've done some similar work, you could pop it up on a github repo or something. What is the game?
Did you forget to tell Claude to make it run fast?
(I am not joking. I did a port of an old utility, Dos Navigator, and I gave Claude+Codex a set of KPIs: cold start under 100ms, 30MB RAW image preview under 50ms, and a few others. I went to bed, and I woke up to a file manager written in Swift that is a joy to use, its so fast, esp. when previewing images. If I haven't requested it, it would likely be way slower).
Jokes aside yeah I'm definitely in need of a ram upgrade. Or I have to learn how to close Firefox tabs.
But with a few docker containers, android studio running an emulator + vscode and a ton of Claude code / Pi / Codex instances, I'm basically maxed out all the time now.
I use about:processes to stop processes that eat up too much memory over time. The tabs stay open but get unloaded. YouTube especially acts like a black hole for memory if you let it.
Under exactly what cooling conditions? All Apple hardware thermal throttles badly because proper cooling is ugly to Apple fans. Form over function is the norm for Apple, so no matter how fast the test results seem, the real-world machine probably will only reach these speeds for a short amount of time before thermal throttling sets in.
According to geekbench 7800x3d is 2400 single core, 15500 multicore. M4 pro is 3350 single core and 24750 multicore. Yet when I convert video using libsvtav1 with ffmpeg I’m getting noticeably faster performance on the desktop. And that’s with mbp, which doesn’t thermally throttle within 15 seconds.
Is it the 96mb cache? Avx-512? Are benchmarks bullshit when comparing different architectures?
Which version of svt-av1 are you using? Neon optimisations were added quite recently in svt-av1, and are still a bit incomplete, so it might make a difference.
Probably AVX-512. AFAIK Apple CPUs are still using ARM NEON instructions with 128-wide SIMD registers. I guess they are banking on you using the GPU if you want to parallelize those kinds of workload.
Zen 4 isn't 512 bits wide though, it's a split cycle 256 bit wide SIMD engine otherwise very similar (except in register size) to M6's.
The answer is more that Geekbench is at this point[1] heavily tuned to exactly the code Apple silicon does well: implicitly parallel wide-issue scalar code that you typically get out of modern compilers and JIT engines when throwing mostly-unoptimized "regular source code" at them. Apple has an enormous amount of instruction issue parallelism compared with x86.
The grandparent is looking at transcoding tasks where the limit isn't instruction issue but actual compute hardware on the core. And Apple doesn't actually win by much there.
It's just hard to know what to measure. Geekbench tends to be a metric for "feels fast doing boring interactive user stuff", which probably matches Apple's marketing imperatives well.
[1] Really they keep moving harder in that direction with every release. The "cooling pauses" in v6 likewise seemed very much like an attempt to boost the score on fanless Apple devices. If one were the type to allege a dark conspiracy, this is a tempting spot.
The cooling pause thing was just a dig at Geekbench, not specific to this discussion (thus putting it in a footnote). They tuned (the last version of their) benchmark specifically to give better numbers on hardware that tends to throttle under performance load.
Now... you can make a reasonable case that this matches real world interactive load better. But it also happens to have the practical effect of making Apple's numbers better, and no one else's. The new benchmarks are measuring subtly different things, and the new thing they measure happens to be what Apple wants to sell. At best, that's backwards.
I think software with a strong focus on SIMD really favours x86 over Apple, since AVX2 support was pretty uniform and AVX-512 (except Intel's fiasco) has been supported for a while, while the post-NEON landscape is strange in ARM country.
X64 does have a stronger SIMD story, but this is partly compensated for by the fact that ARM64 is much easier to decode wide. M series has a very wide decoder and a lot of instruction level parallelism. It can turn chunks of those 128-bit SIMD operations into what amounts to wider operations.
AVX still wins though.
M series still wins on performance per watt and now apparently leads on general purpose code.
All these leading edge chips are very good. We have an embarrassment of riches when it comes to blistering fast chips here.
On what, microbenchmarks? I have realtime audio workloads where the hot loop is essentially linear algebra. Exactly the kind of work that suits AVX2/AVX512. Guess what, Apple Silicon still pulls ahead because real workloads are branchy, cache-hungry, full of dependencies and do not line up in 8 neat f64 operations per cycle.
For parallelisable stuff that can occupy all cores for an extended period, the 2990WX typically takes about ~1.2x as long to do the same work/does ~0.83x the work per unit time, assuming code compiled with clang or gcc. Which isn't really coming across in the numbers here.
I haven't spent much time timing single core stuff, except - regarding clang, which looks like it contributes to the Geekbench 7 score, I did some measurements a few months ago suggesting that clang compiles for x64 more slowly than for ARM, all else being as equal as I could be bothered to try to make it: https://news.ycombinator.com/item?id=46938682 - and the single threaded test runs I did of my code suggest that the Geekbench 7 single core might be about right?
(Whether the clang timing discrepancy is actually relevant to Geekbench, I've no idea, but I thought it interesting anyway.)
If you need a benchmark that makes the PC look massively faster than the Mac, I'm sure those are available too.
Geekbench multi-core has been a single-task benchmark since version 6. The multi-core / single-core score ratio is supposed to tell how much you will benefit on the average when you use all available CPU cores. Some tasks parallelize better, while others have bottlenecks that prevent effective parallelization. For every CPU, the ratio is well below the nominal speedup you can get under ideal circumstances.
Note that Geekbench 7 no longer runs the same subtests in multi-core mode as in single-core mode, so any ratio calculated from the overall scores instead of from the individual subtests is misleading. There are a lot of subtests that it only runs in single-core mode and omits from the multi-core tests, seemingly to placate the critics that didn't like the inclusion of poorly-scaling tests in the multi-core mode. It's not as dumb as the Geekbench 5 strategy of just running N independent copies of the test, but it does seem like a dumb change to me.
Just want to add apart from all the other comments. SVT was brought by Intel and spent years to make it extremely well tuned for x86. While not the same for ARM and not even for Apple.
Another point is that the multicore part uses all core including E-Core. On AMD the multicore are all the same. Meaning for some benchmarks this will flavour Apple more.
Again there is nothing that stop people from optimising it for ARM Mac. The problem is the usage of it is so small it probably doesn't make sense to focus on it. SVT took a really long time for it to reach quality parity with AOM's AV1 encoder and later exceed it.
I know these are all Mac CPU, but for context people may want to look at A20 Pro [1], which in 2 years time will be in MacBook Neo. Pretty damn impressive if you ask me.
A20 Pro is around 4K on Geekbench 7. And the P-Core is not the same as M6. The A20 Pro is actually only 9 wide compared to 10-wide on M6. Supposedly more power efficient and smaller die size.
Apple needs better GPUs for "AAA gaming on macOS". My M2 Max is pretty awful at games that run fine on a desktop GPU. An M(whatever) Ultra to play games seems like a debatable value proposition.
Ah, asking the real questions. The speed of a closed ecosystem CPUs such as Apple's is irrelevant. As long as Linux or BSD doesnt't run on it in a stable fashion, I'm not interested.
It's not even that Linux is that great. But Windows and MacOS user experience have degraded so much in the last decade due to user hostile decisions and lack of vision, they essentially nullify advances made on the hardware side.
I genuinely think that GNOME is more user-friendly than macOS by a wide margin.
The majority of computer users today are familiar with either Windows or iOS/Android primarily. They're not coming from UNIX CDE machines or Macs on-average, they want a desktop that behaves like their phone does and reinforces/rewards their intuition from Windows. They want to click (X) on a window to confidently close it, they want to mash the Start key to search for an app, they want to tap "Install" on a storefront instead of dragging a DMG icon into ~/Applications. All of the little idiosyncrasies that macOS clings to doesn't help people learn it.
I will never understand how an intelligent, opinionated crowd like HN can be so obsessed over Apple's CPU offerings. Buying into the Mac ecosystem is without a doubt subjecting oneself to vendor lock-in. Linux won't even run on these machines until in 2-3 years, if you're lucky.
The OS is mostly invisible to me. Except for the desktop manager but both Mac and Linux have options for that, I just don’t even feel the need to change the defaults. If I really need Linux for whatever reason, Docker makes that extremely easy on my Mac. I really can’t understand what Linux gives you that you would feel a need to change your OS on Mac.
Interesting how people find reasons even when they make no sense. When did you experience problems with Docker on Mac?? I couldn’t care less it’s not native, it just works. About CUDA, mac has great GPUs , so much so that it’s a fad now to buy mini Macs to run LLMs.
I don’t know about why you would use those file systems, am I missing something so great about them?
Package management is awesome on Mac with brew, people are even using Brew on Linux lately since it’s one of the best.
About system updates, I don’t remember being forced to do it, quite the opposite, my old Macs stopped being able to update after 8 years I believe. Which is fine with me, they get pretty obsolete after so long , and I believe Linux Wasabi works on old Macs if I need it ( but I don’t , I have a Dell with Linux that I could use if I wanted Linux, but I never need it and that laptop was just headache for me, which is why I choose to only use my Macs now ). But to each its own though.
> When did you experience problems with Docker on Mac??
On my 16gb Macbook Pro, compiling a monorepo for my job. Between the APFS slowdowns and the virtualization overhead, it was faster to build everything in a VPS and download the artifacts onto my Mac.
> About CUDA, mac has great GPUs , so much so that it’s a fad now to buy mini Macs to run LLMs.
Mac GPUs are close to the worst on the market. There's a reason why AMD and Nvidia are being put in datacenters while Apple Silicon isn't. Apple's GPU designs are a waste of electricity for LLM inference. My RTX 3070 Ti cost $500, is fabbed on Samsung's 8nm node and beats the 5nm M2 Ultra's GPU in power efficiency. That's how bad Apple Silicon GPUs are for compute.
> I don’t know about why you would use those file system
NTFS and ExFAT are the two most-common filesystems of all time. Almost all flash drives and external drives are formatted like this, not HFS or APFS.
> Package management is awesome on Mac with brew
Brew is a dependency graph nightmare. You should be using Nix on macOS if you're a developer, it handles things like side-by-side package versioning and environment isolation much nicer than Homebrew does. Brew works okay for simple app installation, but is basically a torture device if you use it professionally.
You seem to be in a completely different universe than me.
Mac GPU, for consumer products, is absolutely the best when you need LLMs which require a lot of memory and consumes much less power (it's funny that you seem to believe otherwise when that's literally that biggest advantage of Mac silicon which absolutely no one who knows anything about computers doubts).
If you think Nix is great but Brew is not, I really don't know what to tell you. One is a UX nightmare, the other just works. Nix is cool, I admit, but for day to day usage, it really is not ready for real world usage.
Your comments are like a parody of a professional, I highly doubt you're a professional, you're a teen, aren't you? I should've guessed it when you mentioned "High-performance Vulkan drivers" :(.
No driver problems (well, first party ones at least), good performance and I can still run any software I like.
I do prefer and run Linux on my desktop, and could complain about Apple and Mac OS all day. The level of polish is very inconsistent. But despite everything it's still not as user hostile as Windows got nowadays.
"Linux won't even run on these machines until in 2-3 years, if you're lucky"
I have yet to buy a Windows machine where Linux works perfectly with no issues whatsoever. My most compatible machine to date needed a USB-C ethernet adapter to get a network connection for more than 10 minutes at a time.
So ironically old M series Macs might not be the worst choice given Asahi doesn't need to target every hardware configuration of the last couple decades.
Would be interesting to see Speedometer 3.1 tests as well. I find they translate really well to user experience, and previously the M5 Base was beating the equivalent Ryzen/Intel there as well.
108 comments
[ 1.3 ms ] story [ 310 ms ] threadWhere does the myth of Apple come from? You should go on blind and ask someone that works there the reality lolol
I would love to see macOS replacing Windows in virtual desktop environments.
The M7 generation has updated the tensor instructions in the GPU cores and they want to ship that ASAP.
This is actually the M6 Pro and not the M6. It has 18 CPU cores to the M6's 12. The scores line up as well.
Reports have said all along that Apple is skipping M6 Pro/Max to focus on M7 generation.
I can't remember the last time an Apple chip got leaked like this.
In the current times performance/price seems to be increasingly important.
(Not to mention several other factors that once did not even exist, or were irrelevant.)
Or is it just an early advertisement, which it is?
Guess they didn't get the expected # of preorders.
Out of curiosity, I also ported the game to arm Linux with fex + upstreamed the wine patches in about a third the time and there's no FPS issues
In my experience as game developer and porting C++ code tells such difference usually mean there are something really wrong with syncronization primitives. So 99.99% of the time code does nothing just waiting for something to unlock.
Anyway, probably you are trying to run a 32-bit executable with Rosetta, that won't be fast, because Rosetta was never meant to run 32-bit things and has got a lot of pitfalls.
I recommend you try giving your AI an open ended task like, "it's at 4 fps even though it's a 22 year old game and the raw hardware performance is many orders of magnitude higher. Maybe due to running under Wine and Rosetta. Please figure out the simplest way you can unlock usable performance (30-60 FPS) short of decompiling, reverse engineering, and reimplementing the full game yourself natively. Maybe there is something else you can figure out for the performance unlock. The hardware is definitely there, so there has to be a way. The game is running so make sure you don't break it. Keep the same game behavior."
Regardless of which AI you're using, it will be able to figure something out in a few hours. 2004 pc's were 500-800 mhz, 128 MB RAM, and if they had a GPU at all it was 16-32 MB, 0.2-1 GLOP.
Your AI should be able to figure out a way to get it running in realtime.
If you want help, I've done some similar work, you could pop it up on a github repo or something. What is the game?
(I am not joking. I did a port of an old utility, Dos Navigator, and I gave Claude+Codex a set of KPIs: cold start under 100ms, 30MB RAW image preview under 50ms, and a few others. I went to bed, and I woke up to a file manager written in Swift that is a joy to use, its so fast, esp. when previewing images. If I haven't requested it, it would likely be way slower).
For me it's like they built a Ferrari with 4 thin bicycle tires. What a waste.
So this is different and faster than such a result in the old scoring would have implied.
It feels like a crime upgrading from this thing tbh.
But with a few docker containers, android studio running an emulator + vscode and a ton of Claude code / Pi / Codex instances, I'm basically maxed out all the time now.
I use about:processes to stop processes that eat up too much memory over time. The tabs stay open but get unloaded. YouTube especially acts like a black hole for memory if you let it.
AMD beats Intel, but only by a couple hundred points.
Qualcomm beats them both.
Apple’s are on a “2 nanometer” from 2025
M5 Ultra CPU:
https://browser.geekbench.com/search?k=parkdale_cpu&q=mac17%...
M5 Ultra GPU:
https://browser.geekbench.com/search?k=grand_gpu&q=mac17%2C1...
Base M6 CPU:
https://browser.geekbench.com/search?k=parkdale_cpu&q=mac18%...
Base M6 GPU:
https://browser.geekbench.com/search?k=grand_gpu&q=mac18%2C5
According to geekbench 7800x3d is 2400 single core, 15500 multicore. M4 pro is 3350 single core and 24750 multicore. Yet when I convert video using libsvtav1 with ffmpeg I’m getting noticeably faster performance on the desktop. And that’s with mbp, which doesn’t thermally throttle within 15 seconds.
Is it the 96mb cache? Avx-512? Are benchmarks bullshit when comparing different architectures?
Bingo, each CPU is too unique with its own strengths and weaknesses to make broad statements, marketing picks up what they like and ignore rest
Apple chips don't have AVX-512.
They do have media engines (that don't support AV1 encode), so if you switch to H.265, it will pull way ahead.
Zen 4 isn't 512 bits wide though, it's a split cycle 256 bit wide SIMD engine otherwise very similar (except in register size) to M6's.
The answer is more that Geekbench is at this point[1] heavily tuned to exactly the code Apple silicon does well: implicitly parallel wide-issue scalar code that you typically get out of modern compilers and JIT engines when throwing mostly-unoptimized "regular source code" at them. Apple has an enormous amount of instruction issue parallelism compared with x86.
The grandparent is looking at transcoding tasks where the limit isn't instruction issue but actual compute hardware on the core. And Apple doesn't actually win by much there.
It's just hard to know what to measure. Geekbench tends to be a metric for "feels fast doing boring interactive user stuff", which probably matches Apple's marketing imperatives well.
[1] Really they keep moving harder in that direction with every release. The "cooling pauses" in v6 likewise seemed very much like an attempt to boost the score on fanless Apple devices. If one were the type to allege a dark conspiracy, this is a tempting spot.
MacBook Air/neo are the only ones without fans. Even the Studio Display has a fan
Now... you can make a reasonable case that this matches real world interactive load better. But it also happens to have the practical effect of making Apple's numbers better, and no one else's. The new benchmarks are measuring subtly different things, and the new thing they measure happens to be what Apple wants to sell. At best, that's backwards.
From what I've been able to gather, Apple only supports SME and the small "streaming" part of SVE2 required by SME since the M4. Which seems to be mostly useless for video encoding (I only see NEON/SVE in https://gitlab.com/AOMediaCodec/SVT-AV1/-/tree/master/Source... or https://github.com/Multicorewareinc/x265/tree/master/source/...) it's basically a GEMM engine.
So basically, video encoding is bad show for Apple who seem to be saying "use crappy hardware encoding and buy amd64 if you need more".
Very hard to find benchmark data. Found https://openbenchmarking.org/vs/Processor/Apple+M4+Pro,AMD+R... that shows a good x265 performance at 1080p but not 4K. Guess the wider SIMD units matter more there.
Apple has dedicated hardware for video decode and encode for several video formats.
That's why the comparisons between PCs and Macs running video editing software favor the Macs so heavily.
AVX still wins though.
M series still wins on performance per watt and now apparently leads on general purpose code.
All these leading edge chips are very good. We have an embarrassment of riches when it comes to blistering fast chips here.
On what, microbenchmarks? I have realtime audio workloads where the hot loop is essentially linear algebra. Exactly the kind of work that suits AVX2/AVX512. Guess what, Apple Silicon still pulls ahead because real workloads are branchy, cache-hungry, full of dependencies and do not line up in 8 neat f64 operations per cycle.
Geekbench 7 results:
* AMD 2990WX: 1384 (single), 13052 (multi) (https://browser.geekbench.com/v7/cpu/181239)
* Apple M4 Max: 3552 (single), 29863 (multi) (https://browser.geekbench.com/v7/cpu/390256)
For parallelisable stuff that can occupy all cores for an extended period, the 2990WX typically takes about ~1.2x as long to do the same work/does ~0.83x the work per unit time, assuming code compiled with clang or gcc. Which isn't really coming across in the numbers here.
CPUMark is a bit better:
* AMD 2990WX: 2282 (single), 32040 (multi) (https://www.cpubenchmark.net/cpu.php?cpu=AMD+Ryzen+Threadrip...)
* Apple M4 Max: 4590 (single), 43911 (multi) (https://www.cpubenchmark.net/cpu.php?cpu=Apple+M4+Max+16+Cor...)
I haven't spent much time timing single core stuff, except - regarding clang, which looks like it contributes to the Geekbench 7 score, I did some measurements a few months ago suggesting that clang compiles for x64 more slowly than for ARM, all else being as equal as I could be bothered to try to make it: https://news.ycombinator.com/item?id=46938682 - and the single threaded test runs I did of my code suggest that the Geekbench 7 single core might be about right?
(Whether the clang timing discrepancy is actually relevant to Geekbench, I've no idea, but I thought it interesting anyway.)
If you need a benchmark that makes the PC look massively faster than the Mac, I'm sure those are available too.
Go check out blender CPU scores if you need any reassurance that AMD still makes some kind of sense.
https://opendata.blender.org/benchmarks/query/?compute_type=...
Another point is that the multicore part uses all core including E-Core. On AMD the multicore are all the same. Meaning for some benchmarks this will flavour Apple more.
Again there is nothing that stop people from optimising it for ARM Mac. The problem is the usage of it is so small it probably doesn't make sense to focus on it. SVT took a really long time for it to reach quality parity with AOM's AV1 encoder and later exceed it.
A20 Pro is around 4K on Geekbench 7. And the P-Core is not the same as M6. The A20 Pro is actually only 9 wide compared to 10-wide on M6. Supposedly more power efficient and smaller die size.
[1] https://browser.geekbench.com/search?q=iPhone19%2C2
https://browser.geekbench.com/v7/cpu/singlecore
here are the leaderboards for anyone else who was curious
And Windows is not remotely dead yet. Gamers are not selling their PCs and getting Macs.
Not even support for the latest Diablo or Overwatch and absolutely no GTA 6 for example
If someone wants to add qualifiers, they should do that and make it clear.
Been hearing both for the same time.
It's not even that Linux is that great. But Windows and MacOS user experience have degraded so much in the last decade due to user hostile decisions and lack of vision, they essentially nullify advances made on the hardware side.
The best experience I’ve had is with Omarchy 4, but it is not appropriate for average computer users.
The majority of computer users today are familiar with either Windows or iOS/Android primarily. They're not coming from UNIX CDE machines or Macs on-average, they want a desktop that behaves like their phone does and reinforces/rewards their intuition from Windows. They want to click (X) on a window to confidently close it, they want to mash the Start key to search for an app, they want to tap "Install" on a storefront instead of dragging a DMG icon into ~/Applications. All of the little idiosyncrasies that macOS clings to doesn't help people learn it.
People care about performance.
- Native Docker support in-kernel
- Hypervisor without a 2 VM limit
- High-performance Vulkan drivers
- CUDA support (macOS doesn't sign CUDA drivers for some reason)
- Support for NTFS, FAT32 and other common filesystems without using FUSE
- Better package management with versioned rollback
- System updates that don't force breaking changes
Those are just the ones that stop me from returning to macOS (I left after Catalina).
On my 16gb Macbook Pro, compiling a monorepo for my job. Between the APFS slowdowns and the virtualization overhead, it was faster to build everything in a VPS and download the artifacts onto my Mac.
> About CUDA, mac has great GPUs , so much so that it’s a fad now to buy mini Macs to run LLMs.
Mac GPUs are close to the worst on the market. There's a reason why AMD and Nvidia are being put in datacenters while Apple Silicon isn't. Apple's GPU designs are a waste of electricity for LLM inference. My RTX 3070 Ti cost $500, is fabbed on Samsung's 8nm node and beats the 5nm M2 Ultra's GPU in power efficiency. That's how bad Apple Silicon GPUs are for compute.
> I don’t know about why you would use those file system
NTFS and ExFAT are the two most-common filesystems of all time. Almost all flash drives and external drives are formatted like this, not HFS or APFS.
> Package management is awesome on Mac with brew
Brew is a dependency graph nightmare. You should be using Nix on macOS if you're a developer, it handles things like side-by-side package versioning and environment isolation much nicer than Homebrew does. Brew works okay for simple app installation, but is basically a torture device if you use it professionally.
Mac GPU, for consumer products, is absolutely the best when you need LLMs which require a lot of memory and consumes much less power (it's funny that you seem to believe otherwise when that's literally that biggest advantage of Mac silicon which absolutely no one who knows anything about computers doubts).
Real world, proper comparison here: https://www.thinkdifferent.blog/blog/the-truth-about-mac-vs-...
If you think Nix is great but Brew is not, I really don't know what to tell you. One is a UX nightmare, the other just works. Nix is cool, I admit, but for day to day usage, it really is not ready for real world usage.
Your comments are like a parody of a professional, I highly doubt you're a professional, you're a teen, aren't you? I should've guessed it when you mentioned "High-performance Vulkan drivers" :(.
I do prefer and run Linux on my desktop, and could complain about Apple and Mac OS all day. The level of polish is very inconsistent. But despite everything it's still not as user hostile as Windows got nowadays.
"Linux won't even run on these machines until in 2-3 years, if you're lucky"
I have yet to buy a Windows machine where Linux works perfectly with no issues whatsoever. My most compatible machine to date needed a USB-C ethernet adapter to get a network connection for more than 10 minutes at a time. So ironically old M series Macs might not be the worst choice given Asahi doesn't need to target every hardware configuration of the last couple decades.
IME intelligent people don't have difficulty understanding that different people want different things.