Not exactly "future proof" for >1T parameter models but good for targeting specific lower-parameter models, or if you can rely on pipeline parallelism and run a cluster.
Computers are never "future proof".
Upgradeable components however could go a loooong stretch towards that goal. It can't be that hard to follow a common form factor for at least the housing across two or three generations to allow a reuse of everything but the main PCB.
Well it might be an idea to keep the layout of the mainboard and connectors the same.
That way, instead of having to upgrade the whole machine, all it would need is a new mainboard. Framework for example managed to pull that off, and in mobile at that, where constraints are much worse than for a desktop computer.
It's not the same thing though. On the M-series, CPU and GPU share a unified memory architecture and ram is much more tightly coupled to get it to go faster. A closer example would be the Framework desktop, actually, where memory is also soldered in for the same reason.
It’s a very non-Apple thing to do, but it’d be pretty awesome if they did.
Would be nice if someone knowledgeable about electrical engineering and manufacturing processes could lay out some valid reasons for manufacturers to integrate RAM onto the motherboard.
The SO DIMM Ram slot, which is designed, idk, 30 years ago? is not really capable of handling the frequency we are targeting (close to 10GT/s)
It was future proof but not really because it struggled a lot in its final years.
I expect it to stay a mediocre gaming PC for the next 3 years maybe 5 years.
16GB RAM RTX 3060 TI (8 GB VRAM)
I also like 4K with 90 to 120fps which leads me most of the time to use almost minimal settings.
Look at steam hardware reviews. My setup is quite the default thing. Games optimize for it
And if not, would you consider a raspberry pi a computer? or your iphone a computer?
i'm still using an old i7 3770k @ 4.8ghz with 16gb (ddr3) ram running linux for random tasks like executing tests. obviously, power consumption is higher.
my main machine is a MBP M1 Max which i use for everything. i also have my main linux desktop workstation that has a 5950x with 128gb (ddr4) ram.
i'll probably get 2-5 years out of my MBP, and my AMD workstation will probably be good for another 5-10 years.
i'm not a gamer, but i have a 3080. i'm sure my 5950x will still be good for gaming in 10 years if paired with a modern GPU.
A 8 years old graphics card can still play modern games. Ten years ago playing a modern game on hardware that old would've been unthinkable.
And with how the market is right now, we'll be stuck on the current "reference level" of hardware for a while longer.
My thinkpad t14g1 with 16gb ram somehow still relevant today.
I don't play games, but it still chugs along perfectly fine and for what I use it for I rarely think that it's too slow.
To me there is no reason to update a PC if you don't use Windows or MacOS that forces you to purchase a new hardware to do the same things. Just look at Windows 11, full of useless AI features, weights a ton, and in the end it's probably faster a PC from 25 years ago with Windows XP.
A NVIDIA RTX 6000, 96 GB at 1.7 TB/s, is 13 grand.
This 256 GB at 1.2 TB/s Mac is extremely competitive, it will be sold out everywhere.
If you can show me a model for which a Mac is faster than the RTX 6000 then I’ll be happy to update or retract my statement.
I can run agents using deepseek v4 flash or Qwen 3.8 on my m3 ultra and it will be lukewarm and the fan will eventually start blowing softly.
Yes, the Mac might get lukewarm, but it will take 2-3+ times longer to do the same task.
Also while the pre fill performance sucks, the Mac isn’t that slow and can use much better model compared to a similarly priced Nvidia workstation so it’s not really taking much longer in practice.
It’s taking longer than in the cloud for sure. At least a local computer uses the local energy grid that is pretty clean and not fossil energy.
> Also while the pre fill performance sucks, the Mac isn’t that slow and can use much better model compared to a similarly priced Nvidia workstation so it’s not really taking much longer in practice.
This is exactly backwards; assuming you mean that the Mac has more RAM so you can use a larger model, the mac is going to be _even slower_ since the fastest Mac isn’t as fast as the average nVidia setup.
My point is that comparing apples to apples (no pun intended), an nVidia setup is both faster and (possibly with some tweaking) more efficient than a Mac.
RTX 6000 wins in performance, if your model can fit into the VRAM.
There are very obvious and clear advantages to a Mac Studio. It's an entire system for one and you're getting a world class CPU as well.
[citation needed]. I have personally specced out and built an nvidia GPU-based machine which after some optimization, handily beat the Mac Studio in terms of tokens/watt for LLM inference with most models. This was in the M2 Ultra era, and I haven't run the numbers for the later generations, but nvidia's cards have gotten faster just as Apple's CPUs/GPUs have, so I would guess that it's still possible to do.
> RTX 6000 wins in performance, if your model can fit into the VRAM.
"if your model can fit into the VRAM" can be true for the Mac as well.
> There are very obvious and clear advantages to a Mac Studio.
There are certain advantages for sure, depending on your use case. They may _seem_ to be obvious, but as evidenced above, I believe that many people overestimate the Mac's superiority on the metrics you cite when comparing a Mac vs. a dedicated GPU for LLM inference.
It is much more likely for your model to fit in large unified memory of a Mac than the smaller more limited memory of a GPU. Even going with two 5090s, you now have to shard your model and that is a PITA.
But it turns out that MoE is the solution both for running models on macs of limited computer power means (not as fast as GPUs), and on multiple GPUs that require sharding the model.
I bristle at general statements like this when it obviously depends on the specific Mac and GPU in question. But yes, comparing a maxed out M5 Ultra with an RTX 6000, the Mac has much more memory.
> Even going with two 5090s, you now have to shard your model and that is a PITA.
Every modern tool does this for you automatically. It is absolutely not a pain in the least (e.g. llama.cpp ships with pipeline parallelism enabled by default).
If you are using multiple GPUs, MoE is basically going to be your only workable choice unless you can leverage pipeline parallelism (only half your GPUs can work on a prompt at a time, so you need to process prompts back to back in a pipeline setup, and they better be doing similar things because your vram is limited).
I’ve got a 4060 ti 16gb, and I’m thinking about getting another. I previously specced out a cluster using multiple 3090s. At the time, the 3090s were going for $700 on eBay. They’re more than that now, but there’s no need to spend $4k per GPU at all.
[citation needed].
RTX 6000 wins in performance, if your model can fit into the VRAM.
> Mac studio wins in memory capacity, price, perf/watt and value.
This is a good video to watch.
Yes, I agree.
> What about [...] performance per watt which I’ve now mentioned ~~four~~ five times and you’ve ignored the previous ~~three~~ four times?
The video was not focused on performance per watt at all, and the best attempt that the video makes at measuring performance per watt actually shows the opposite: that the 5090 system is more efficient than the Mac.
When he's running the 27B model, at about 5:02, he shows that the Mac Studio is pulling 251.5W, and the PC is pulling 315.3W.
Then he shows the results:
Mac: 27.62 tok/s PC: 40.92 tok/s
Doing the math, we arrive at 0.11 tokens/W for the Mac, and 0.13 tokens/W for the PC. The PC is about 20% more efficient.
The only other time he even shows the power usage at all is near the beginning, running a 4B model which is trivially small for both systems.
So once again, I ask, what are the sources for your performance/watt claim?
Good for inference; however if you like to train, data format support and effective performance is limited (M5 Pro). Some hardware features are not exposed or extremely slow.
You’ll be fine for inference, but pales in comparison to what a RTX 6000 Pro can do for compute/matmuls/training.
If you just want to run Qwen 3.8 27B and Deepseek v4 Flash in perpetuity and that's it, there are a lot of solutions that will work and this is a fairly user friendly one.
Lastly, I want to clarify that prefill on an x86 CPU is drastically slower than on an M5 Ultra GPU.
It feels like PCIe is a bit of a boat anchor here. There's a SATA->NVMe style transition waiting in the wings to make this all so much better. We really need post-PCIe GPUs. CXL with it's very small low latency flits. This is an "almost certainly not" but I wonder if you could mix PCIe and CXL so you could have the GPU memory expose vmeme as a bunch of CXL.mem pools but still have an otherwise pretty normal GPU. It seems madness that UALink went all in on GPU-to-GPU with no affordances for connecting to host computers.
But my next machine for LLMs will probably be the Mac Mini (with 64GB vRAM access) for low-$2300s – which is what I paid for my MC-Prebuilt (and am still very happy with – Ubuntu is great).
After decades of installing and forgetting various shades of linux-distro, Ubuntu has kept me "using" the computer as a tool, instead of "just tinkering with it").
But, that doesn't make it a good deal. It just means the Apple tax doesn't apply when stacked up against AI machines and with memory prices being so out of whack. I'm still planning to wait until the RAMpocalypse ends before I buy any more hardware.
Otherwise you'll have to wait to see if the AI circular financing club collapses- if you still have a job, there should be deals to be had...
Efficiency is improving, both in hardware and in software and in intelligence density (smaller models can effectively do more of the AI work that needs doing), so I think the pure data center plays will falter. If there isn't some other business attached, they're never going to recoup their investment. Anthropic and OpenAI are buying all the compute they can find right now, but efficiency gains, especially those coming out of Chinese labs where they must be more efficient to compete, will make it less and less of a problem.
I mean, think about the hardware we use for AI. It's basically an accident. GPUs were not designed for AI (though they are becoming more focused on AI). The specialized AI hardware industry is just ramping up.
So, we're still early in the curve for how efficient both the hardware and software can be at performing these tasks, and given the effectiveness of recent very small models (e.g. DeepSeek V4 Flash 0731 and Qwen 3.8 27B), I just don't see a long future for giant data centers built around billions of dollars worth of last years graphics cards. As with the crypto mining operations, at some point, it becomes more expensive to run the hardware than it makes in revenue. And, as with the crypto mining operations, when the money dries up, the hardware hits eBay and prices drop.
RAM production is completely sold out for 2027[1] which means the prices are locked in until after then.
It takes about 2 years from the time ground if broken for a new fab to be built and producing RAM.
There were some new fabs announced between February and April this year by both the Korean and Chinese manufactures, so that new capacity might start having an impact in 2028 in the most optimistic scenario.
Samsung says supply will remain tight in 2028[2], and Micron says "tight beyond 2027"
The best hope is that new (Chinese) players overbuild fab capacity and supply outstrips demand. That isn't likely, but perhaps in the late 2028-2029 timeframe could happen.
[1] https://www.techpowerup.com/351344/memory-makers-seal-2027-d...
[2] https://www.tweaktown.com/news/112966/memory-shortages-will-...
[3] https://s25.q4cdn.com/621799436/files/doc_events/2026/06/Q3-...
Producers (Samsung, SK Hynix etc.) will not say "prices expected to drop" or "demand expected to drop" even if it was true because then consumers would start delaying purchased.
The big buyers (OpenAI, hyperscalers etc.) have no incentive to say "supply expected to start opening up" because that would imply their growth trajectory is flattening; also a huge part of their moat now is just deployed RAM.
When memory prices come back down, I'll be down to the Apple Store. But, it doesn't make sense to buy hardware right now.
I bought a refurbished M3 Max a couple of years ago just to try things out, I get 90 toks/s which is good enough for a lot of tasks. But ya, when DRAM prices come back down I'll definitely look for a better local rig.
- 120v input plug
- not rack-mounted
- has a video out port
Hence why they had to make up the "Studio" brand for the workstation market, because they'd already fully removed any meaning from "Professional"
Putting aside the fact it is a marketing label, "Pro" usually means "designed for work" while "Consumer" (in this context) means "doesn't need a special environment".
In computing the distinction is primarily noise, power and cooling requirements.
If a computer is designed to use home power and is quiet enough to use without annoying people and doesn't require specialist cooling then it is a consumer device, even if it is used for work.