I like Framework and own one of their laptops. But the desktop seems more a triumph of gimmicky marketing than a desktop that's meaningfully different. And, it seems significantly overpriced.
Framework Desktop price with default selections, 32GB of RAM, 500 GB storage: $1,242.00 USD
Mac Mini with 32GB of RAM, 512 GB storage: $1,199.00
Post changed a bit since I started replying, so:
> For the purposes of running LLM models, a Mac Mini
The M4 Max is the one that actually gives you a shit load of memory bandwidth. If you just get a normal M4 it's not going to be especially good at that.
> it doesn't have MacOS
The Mac can't run Windows, which is used by ~75% of all desktop computer users and the main operating system that video games target. I'd say that would be the bigger problem for many.
> Apple's service
What advantage does that get you over Framework's service?
> resale value
Framework resale value has proven to be excellent by the way. Go to eBay, search "Framework Laptop", go to "Sold Items". Many SKUs seem to be retaining most of their value.
(Nevermind the ease of repair for the Framework, or the superior expandability. If you want to expand the disk space on an M4 you need to get sketchy parts, possibly solder things, and rescue your Mac with another Mac. For framework devices you plug in another M.2 card.)
Microsoft's AMD64 emulator is slow and buggy compared to Rosetta, and you will need it a lot more, too. Many apps will need to rely on this, including programs many users will immediately try to use, like Visual Studio. Neither Visual Studio nor its compilers support running on an ARM host; it does seem to basically work, but is slow, which is not good considering Visual Studio is already not particularly fast. It will even display a message box warning you that it is not supported during setup, so you couldn't miss it (note that this applies to the Visual Studio compilers needed by Python and Node for installing packages with C extensions). MSys2 gave me a lot of trouble, too; the setup just doesn't seem to work on ARM64. Chocolatey often installs AMD64 or x86 binaries on ARM instead of native ones; sometimes native ones don't exist anyways. Third party thing that needs to load a kernel module? Don't bet on there being an ARM64 build of it; sometimes there is, sometimes there isn't. WinFSP has a build, many hardware drivers I've looked at don't seem to (don't laugh: you can pass through USB devices, there is sense in installing actual hardware drivers.) I just set up a fresh copy of Parallels on an M3 Mac a couple months ago, I'm stopping now to be terse, this paragraph could easily be much longer. It would suffice to say that basic Windows software usage is a lot worse on Parallels than a native Windows AMD64 machine. Very useful, sure. At parity, oh no. Not close.
That's just the basics though. For GPU, Parallels does do some D3D11 translation which is (a lot!) better than nothing, but you are not getting native performance, you are not getting Vulkan support, and you are certainly not getting ROCm or CUDA or anything equivalent, so actually a lot of apps that practically need GPU acceleration are not going to be usable anyways. Even if a video game would run, anti-piracy and anti-cheat measures in lots of modern games detect and block users using VM software, not that you can expect that all of the games you want to run would even work anyways on ARM; plenty of games are known to be unstable and some don't work at all. There are other side effects of trying to do actual gaming in VMs in general, but I really think this gets the point across: Windows games and multimedia are significantly worse in Parallels than on a native machine.
Parallels filesystem bridging is impractical, it's not fast enough and it is buggy, i.e. running Bazel on bridged files will not work. This means you need to copy stuff back and forth basically all the time if you want to work on stuff natively but then test on Windows. Maybe this is partly Window's fault, but in any case it would suffice to say that workflows that involve Windows will be a lot clunkier than they would be on a native Windows machine.
I think these conclusions, that a native Windows machine would be a lot better for doing Windows things than a Mac running Parallels, is actually pretty obvious and self-evident, but reading what you said might literally give someone the opposite impression, that there is little reason to possibly want to run Windows. This is just misleading. Parallels is a great option as a last resort or to fill a gap, but if you have anything that regularly requires you to use Windows software or test on Windows, Parallels is not a very serious option. It may be cheaper than two machines in fiat currency, but probably not in sanity.
I don't know you, so I can't and won't, based on a single post, accuse you of being a fanboy. However, this genre of retort is a serious issue with fanboyism. It's easy to say "Windows? just use VMs!", but that's because for some people, actually just using Windows is probably not a serious option they would consider anyways; if the VM didn't work for a use case they'd back up and reconsider almost anything else before they reconsider their choice of OS or hardware vendor, but they probably barely need (if at all) a VM with Windows anyways. If this feels like a personal attack, I'd like to clarify that I am describing myself. I will not use Windows. I don't have a bare metal Windows machine in my house, and I do my best to limit Windows usage in VMs, too. Hell, I will basically only use macOS under duress these days, I'm not a fan of the direction it has gone either.
Still, I do not go around telling people that they should just go switch to Linux if they don't like Windows, and that Virtualbox or Wine will solve all of their problems, because that's probably not true and it's downright dishonest when deep down I know how well the experience will go. The honest and respectful thing to tell people about Linux is that it will suck, some of the random hardware you use might not work, some of your software won't work well under Wine or VMs, and you might spend more time troubleshooting. If they're still interested even after proper cautioning, chances are they'll actually go through with it and figure it out: people do not need to be sold a romantic vision, if anything they need the opposite, because they may struggle to foresee what kinds of problems they might run into. Telling people that virtual machines are a magic solution and you don't have to care about software compatibility is insane, and I say that with full awareness that Parallels is better than many of the other options in terms of user friendliness and out of the box capabilities.
I think the same thing is fair to do for macOS. With macOS there is the advantage that the entire experience is nicer as long as everything you want to do fits nicely into Apple's opinionated playbook and you buy into Apple's ecosystem, but I rarely hear people actually mention those latter caveats. I rarely hear people mention that, oh yeah, a lot of cool features I use only work because i use Apple hardware and services throughout my entire life, and your Android phone might not work as well, especially not with those expensive headphones I think you should get for your Mac. Fanboys of things have a dastardly way of only showing people the compelling side of things and leaving out the caveats. I don't appreciate this, and I think it ultimately has an overtone of thinking you know what someone wants better than they do. If someone is really going to be interested in living the Mac life, they don't need to be mislead to be compelled.
You're looking at the wrong Mac Mini. The model with the M4 Pro is the right comparison, on account of also having a 256-bit memory bus giving substantially higher bandwidth than a typical desktop computer. The M4 Pro model doesn't have a 32GB option.
The M4 Max (not available in a Mac Mini) has an even larger memory bus, giving it far more bandwidth than either the M4 Pro or the AMD Strix Halo part used by Framework.
The Framework Desktop Max+ 395 with 128 GB of RAM, and a 500 GB SSD costs around $2,147.00 USD before tax. The M4 Pro with the 20-core GPU, 64 GB of RAM, and a 512 GB SSD costs around $2,199.00 USD. That's still short 64 GB of RAM, of course.*
The lowest-end M4 Max Mac Studio that can support 128 GB of RAM seems to cost $3,499.00 with 128 GB of RAM and a 512 GB SSD. For that you get 546GB/s of maximum memory bandwidth according to Apple, which is definitely a step up from the 256GB/s maximum for the Ryzen AI Max+ 395, but obviously also at a price that is quite higher too.
Apparently though, 128 GB of RAM is currently the ceiling for the M4 Max right now. So it seems like if you were going for a maximum performance local AI cluster at any price, the M3 Ultra Mac Studios are definitely in the running, though at that point it probably is starting to get to the price where AMD and NVIDIA's data center GPUs start to enter the picture, and AMD Instinct cards measure memory bandwidth in terabytes per second.
* Regarding GPUs: The Framework Desktop Max+ 395 Radeon 8060S seems to be vastly faster than all of the non-Max M4 SKUs, for anyone that cares a lot about GPU performance. The M4 Max seems to outperform the 8060S by a bit though, and obviously it has some stand-out features like a shit load of video encoding/decoding hardware. This complicates the value comparison a lot. The Radeon core definitely gets a much better value for the performance in any case. I'm really impressed by what they managed to do there.
If the purpose is running LLMs non of that matters.
But Linux support is an advantage. Does the M4 have that?
I run Linux containers all the time.
The LLM point is that Linux is better suited for most AI tools and their toolchains
For desktop you already have thousands of choices though and reparability, assuming its not some proprietary Dell/HP desktop, is already as good as it gets without breaking out your soldering iron.
That said, they'll know more about the market demand than I do and another option won't hurt :)
Strix Halo is almost like having a PS5 or Xbox chip but available for the PC ecosystem. It's a super interesting and unique part for GPU compute, AI, or small form factor gaming.
Of course this PC is interesting in that it’s more “workstation class” and I’m not sure how much thermals matter there, but maybe this is an iteration towards a Mac Studio like device.
Pair a power-efficient mobile chip with a mini-desktop form factor and a good (i.e. probably overengineered, to some extent) cooling solution, and it will give you a kind of sustained performance and reliability over time that you just aren't going to get from the average consumer/enthusiast desktop chip. Great for workstation-like use cases that still don't quite need the raw performance and official support you'd get from a real, honest-to-goodness HEDT.
The only selling point is the form factor and a massive amount of GPU memory, but a dGPU offers more raw compute.
All those SteamOS handhelds are on AMD.
This is literally the limitation of the platform. Why even bring that up? Framework took a part made by AMD and put in their devices.
From the product page I don't see how that mainboard is more repairable than a typical ITX one though. As far as I can tell, you also cannot change the CPU on it so even less than a typical desktop mainboard.
Exactly. Between those three companies, only one of them is likely to even try to make something like core boot possible on this machine. That’s something I can afford to encourage.
I think that might be overstating it a bit. Real "rugged" laptops do exist, and would be quite at home in that kind of use (well, usually you'd worry a lot more about how kids in primary school will treat your hardware than teenagers) but the Framework 12 is not one.
All school laptop fleets I've seen are simply the cheapest thing they can buy in bulk, when it breaks provision a new one.