I don't understand why someone would buy this. It's $1700 for the same computer as a $900 Mac mini. The antiquated 24" monitor, keyboard, and mouse are not worth the extra $800. You can buy a very nice 32" monitor and better input devices for less than that.
That 32" monitor will have a crappy pixel density. It's incredibly hard to find good external monitors that are not made by Apple, definitely not for $800. Apple will give you a display with a high pixel density and glass front.
I wish they would make big displays again. Like 32” big 6K.
24” or even 27” feels like such a downgrade.
Also please make the iMacs usable as external monitors agains. Would buy one as a “livingroom computer” instantly if it was also possible to occasionally use it as a docking station for an air..
I've been using a new program called RetinaRelay[0] to use my 5k iMac as a second display for my M1 Macbook using an ethernet (or Thunderbolt for even better performance). Works brilliantly. It's definitely higher latency than a normal monitor (my ethernet connection is 45ms vs 5ms for a monitor) but it's not noticeable for coding and miles better than remote desktop or similar.
I’m still angry that they deprecated target display mode. For a company that talks so much about recycling it’s really messed up they don’t support it. Such an amazing way to give life to old but incredible monitors - you’d have to spend $1000+ to get anything remotely resembling the quality of that display. You can’t even use ones that previously supported it on current Mac’s.
Absolutely. The display on the iMac 5K was amazing. Ended up giving that machine to a nephew of mine when I moved to Apple Silicon but Apple really dropped the ball here.
We're getting close to local AI being really useful. Before the M1 is dead we might have already seen a huge shift. In my mind, there are two types of macs: those that have the bandwidth to run local models (Max & Ultra) and those that don't (Base & Pro chips).
The generation doesn't mater as much to me as the memory bandwidth. When that day comes, I'd rather have a M1 Max 64GB over a M5 Pro 64GB.
Local AI already is really useful. This has been true since Qwen Flash Next and Qwen 3.8 27B rolled out. The struggle with exactly 64GB of unified RAM is that you end up having to stream the engram table from SSD because you will need almost all of your 64GB to run QFN. A 27B dense model still runs a little slow, even on an M1 Max Mac. However if you have even an older gaming GPU with 12-16GB of RAM and enough system RAM you can run this model (QFN) at a very respectable token rate and intelligence level. It is a Sonnet 5 class model you can run at home. There are new quantization techniques that make these models very good at agentic tasks.
And now if you stretch you can run DeepSeek Flash 4.1.
And if you were willing to roll up your sleeves you could build your own AI lab at home and run this model and models like GLM Flash 5.3 and DeepSeek Flash V4.1 at lower quants. The budget GPUs (like V100) are kind of not budget now, but still <5K to acquire 128GB of fast VRAM that can compete with a 5090 and actually has a lot more interesting options available IMO.
Can share a good way of running Qwen 3.8 27B (or similar) on 16GB VRAM? I've been trying but I end up with either a heavily quantized model or a small context or a slow speed.
I asked Claude to come up with 7 problems to solve that were not part of any benchmarks. Besides speed, I asked it to put together a scoring that would reflect models that perform well on the 7 problems and in a reasonable time-frame (RWS, the definition is in the artifact). I valued models that produced good answers in a reasonable time better than models that had very high throughput but kept spitting useless stuff. Overall, IIRC most of them still had a >30% chance of producing wrong/non-working replies.
I then tested Strata ( https://github.com/niko1221/strata ) and the results are not even close. You can basically ignore everything in that table and use Strata instead, you can use bigger/less-quantized models and have way better results. Basically any otherwise-decent model degrades noticeably at Q < 5, and KV cache at Q4 also contributes a lot.
Still, a 20$/mo Claude subscription is way cheaper/more efficient if you code 2-3h in the evening than running stuff locally, unless you really have hardware than can hold models that get most things right at the first try. You can iterate way faster and cover a lot more ground in 2-3h using a Claude subscription, or OpenRouter if you prefer to change models. You get faster replies that are 99% correct at the first try, whereas using the local model you'd be spending 30% of your time fixing things that don't work and prompting it to do better.
Nowadays I use the local model to delegate tasks that would burn a lot of tokens, like sifting through big data archives for indexing and such.
The easiest thing to do (takes 5 minutes) is to use LMStudio and then search for the model inside LMStudios UI.
It will show you on the model selection IF a model fits and if you use a "Qwen 3.8-35B-A3B" type of model, it should just work out of the box. A3B stands for Active which means you need a lot less fast ram.
You will run into issues fast though: If you have big tasks for it to do, your pc/mac will get warm very fast and noisy and you will cosume relevant more energy.
Dense models are not well suited to this. Depends on your system, but most inference engines let you put the KV cache on the host. They should let you use "Q8" KV cache format as well which takes half the storage of bf16, the default format. You essentially are stuck at having to fit the entire dense model into VRAM because it must compute across the entire model every token. Without it being in VRAM it is slow. MoE models such as Qwen 35B with 3B active parameters are much friendlier to limited VRAM systems. This is why you see systems with 16GB of VRAM running something like DeepSeek Flash if they have a bit of spare system RAM. Usually not at any good token rate, but tolerable.
Dense models also don't like quantization as much and are less tolerant of it. There are some very interesting smaller models like https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4... Dory that I would check out. You need system RAM or to stream a larger MoE model from disk and it won't be fast. You need to specialize the models some to get quality results if you have very limited system resources.
My setup is a Ryzen 3600, 90GB DDR4 allocated to a VM (don’t even really need that much, just had it available, special thanks to the year 2024), and an RX 9060XT 16GB ($500 GPU).
I get around 40-60 tok/s depending on the quantization level I choose.
As you can see, the CPU is nothing special, don’t even need DDR5.
Yes it runs on all levels of hardware - with the latest Strata my 5090 and 64GB DDR5 gets 200-240 tok/sec decode, 6500 tok/sec prefill. Around $0.09/M tokens in power usage (have excess solar capacity).
Jealous, lol. But I did spend a grand total of $500 for my setup. The rest of the server was built purchased with the use case of running game servers.
AI harnesses like Claude will set it all up for you, you can just say "I want to run a localllm on this machine" and it will find the best one for your hardware and even help you fine tune it etc
You will end up with a sub-par result. The space for small models is more specialized and specific and you should optimize to the specific task and or tasks you want to do. It will get some local model working, but there are a lot of interesting small models in the 4-10B space to look at and play with for your specific tasks. If you expect a full agentic coding agent it's just not going to happen without a larger model like Qwen 35B and ... that is not that great by today's standards, even Muse Glimmer is better.
After arguing and back and forth with Claude (not straight away), it found a kv streaming fork of llama https://github.com/achyudh/llama.cpp and an interesting ascii only model Qwen3.8-27B-ASCII-Condensed-UD-IQ4_XS.gguf . It's running, i'll see how it goes.
That's only part of the issue - prefill is horrible prior to M5 class chips.
So it depends on what you're doing. Using it for a fun oracle without feeding it too much context per turn? Sure, an older Max chip is great.
As a coding agent doing meaningful work on a sizable project? Compared to a cheap as chips cloud option, it will take an order of magnitude more time to complete.
Prefill isnt a huge problem with an MoE, but ya, dense models are a non starter before the M5. You are still better off using DeepSeek than a local MoE, but locally running something gives you possibilities if you are on an airplane without internet, or if you want to jump guard rails, or if you want to run a home device server, etc…
Running Gemma 4 26B A4B and Qwen 3.8 27B on a M4 Pro with 24 GB - Qwen 3.8 runs fine but is slow and taxes the machine a bit, Gemma 4 on the other hand, is a better experience.
Puh i don't know, there might be plenty of new/better chips coming out for AI next year or in 2 years.
Isn't it also rumored that the M7 is reworked for AI?
And Xiaomi announced their AI Cube with 1.2t of bandwidth. Just because Nvidia is protecting its business by giving consumers either compute or bandwidth and Apple being something in between, doesn't mean we can't get both a lot better balanced.
Yeah, the price is so high and things are moving so fast I don’t wanna risk committing to something that becomes obsolete in a year. I wanna see the rumoured M7 first. Hopefully hardware demand doesn’t make waiting a stupid decision…
I'm running qwen 3.8 flash next with strata (q3 quant) on laptop with 5090 and 128G RAM and OMP harness. At 90t/s speed it is pretty much good enough already.
Probably not. The ROI for local AI is pretty terrible at best it's like 20 years to see a cost advantage. Most enterprises are going to be fine using hosted models. The two main reasons to use local AI are 1. education and 2. if you cannot use hosted AI for your use case (safety guardrails, payment restrictions, etc.)
>The generation doesn't mater as much to me as the memory bandwidth
I don't know man?
The generation kind of does matter. I'm not gonna lie, matrix multiplication units speed things up considerably. That hardware confers a material change in capability.
Maybe from M5 up, it doesn't matter? But you're definitely going to notice the difference between M1 and M5 for instance.
> I'd rather have a M1 Max 64GB over a M5 Pro 64GB.
I am one of those: bought the M1 Max with 64gb thinking in running VMs, afterward bought a lighter Air with less memory and ended up using the M1 Max as a kind of luxury for LLMs and multicore computing.
Considering the insane memory price surge it's going to take years (or an eternity) before most people will consider upspecing their machines to run local over paying $20 per month to have the honor to loan a slice of Altman's hardware.
The only hope we have is the AI bubble bursting, but that will undoubtedly come with its own set of macroeconomic surprises.
The ~$1T/y AI capex isn't remotely sustainable. Memory fab capacity will go up, AI datacenter provisioning will go down, prices will become reasonable.
Still on my M1 Max 64GB from release date. Love it. I don't do local AI but this laptop runs so cool and fast I have no reason to upgrade. They really knocked it out of the park on the design.
It feels just as fast as day 1 and I've never had any speed issues. Say what you want about Apple and their pricing and ecosystem but I've been using their hardware for over 20 years now and it's always been top notch.
If you buy their support/AppleCare, your support and warranty is excellent too. They don't skimp. I've seen them go so far past the extra mile it's unreal.
This is also my experience, but when I saw how few tokens/second with a large model it gets locally I was bummed. I’m wondering if I’ll be obligated to upgrade in the near future
I jest...but I'm disgusted by the price gouging going on. Glad my hardware is relatively recent and I had mostly maxed out already when I bought it a few years back. The same setup today would be closer to $7k with equivalent parts.
The modern iMac is the dream desktop that I'm sure Jobs would have loved to live to see, but Apple's laptops have gotten so good there's practically no reason to buy a computer from them that you can't take on the go.
It only makes sense for niche use cases, like your grandpa who is happy to have a single spot in his home for the computer, or a reception desk at a business, etc.
This is basically 99% of the proposition of the iMac at this point. If you don't need the specific all-in-one, color, and other design aspects of the iMac or can afford a Studio display, there's no reason not to buy some other display + a Mac mini or a laptop + display
I actually think a desktop makes sense if you want to run local LLMs. I have an M4 Max laptop left to me when I got laid off. It can run good-sized LLMs, but the system heats up, the fans blast off, and it rips through the battery in under an hour. I'd rather have a desktop set up as a private inference server that I could connect to remotely.
Bingo, desktops are still king for actual raw processing. Apple laptops are great, but they're still just computers, given proper cooling and power they can perform even better.
The new post Jony Ive design and limitation to 24 inches make it undesirable. I know a lot of folks with older 2007 - 2019 iMacs but none of them who upgraded from those have the new 2020+ one.
I think it's mainly that from 2006 to 2019, the iMac was the only mid-tier desktop that Apple sold. Today, you can get a Mac mini or MBP that's the same or faster than an iMac.
Though I have had good results buying 1-2 generation old refurbished Macs as my secondary machines or for family members who don’t need cutting edge everything.
It’s even more valuable now that Apple silicon of every generation is more than enough to run every non-power user use case short of newer video games.
The panel is incredibly thin, but the base is a few inches, and the amount of space it will take up due to tilting the display is also a couple of inches. After a certain point, thinness is a meaningless aesthetic choice that serves no function whatsoever.
The one place where size and thickness don't matter is when it's a non-portable device.
I'm surprised they haven't yet gone the route of making a hyper thin screen and hiding the actual cpu somewhere else (something akin tot he puck for the Apple Vision display). Hell you could probably do a proprietary wireless signal and have the display be completely detached. (Or existing wifi6 or something?)
The edges of the thin monitor could be actual transparent glass.
Thinness has been frivolous aesthetics since Steve Jobs times. A thicker laptop will always mean better thermals, more silence, more battery, repairability, more ports.
Its brand differentiation, and hoping that folks associate the ability to make thinner products as "better technology". Which they seem to, especially when paired with a high cost. I'd be surprised if one of their initial mockups didn't have a transparent bezel around the screen (or the screen itself!) to make it look like a minority-report style screen
In a laptop though that thinness and its compromises might actually provide some positives to the product: lower weight, easier to carry in hand or in a bag
On a desktop you view face on, who fucking cares how thin it is?
They seem to want those who would’ve bought a high spec iMac (or briefly, an iMac Pro) to instead buy a midrange-or-above Mini or a Studio instead. With the M-series, the iMac returned to its roots as the “family computer” or “grandma email box” kind of machine.
It’s too bad. A high end iMac still holds a lot of appeal, especially for those seeking clean desk setups. I’m using an MBP hooked up to dual monitors through a dock right now and it’s fine, but I do miss how clean my desk was back when it was a VESA mounted iMac Pro and companion monitor.
I was just thinking the same thing. The M-series is so good, the demand for uber-desktops is smaller than ever. And all professionals I know truly want/need the portability of a laptop.
the iMac returned to its roots as the “family computer” or “grandma email box” kind of machine.
My preferred setup would be a semi-beefy desktop paired with a highly mobile laptop, which with the current product line would be something like a Studio (or a high end 27”/32” iMac, if such a thing existed) and 13” Air. I ended up with an MBP due to constricted availability of the Studio/Mini, though.
I’ve felt the same way since way back then ever since reading about this guy’s setup[0], so I paired a 11” MBA with the quad core Mac Mini 2012.
I’ve kept that philosophy over the years, the MBA was replaced by the 2017 12” retina MacBook and then again with the 13” M2 MBA. The Mini gave way to the 2018 Mini, then a M1 Max Studio. I even attempted replacing the MacBook with an iPad though that didn’t really workout.
It’s the best of both worlds really, enough power to do everything when on the go and even more power back at the office.
Back in the Intel Mac era, it used to be that running even a single docker/vagrant container would bring any MacBook to its knees, so having a nice beefy machine for doing the Real Work was useful while the MBs were mainly used for lighter work loads while on the go.
Nowadays, the M series chips are so powerful that I’ve not had a real need to use my Studio and work mainly using my M2 Air.
The whole point of having always on machines is you can close your laptop and the rest of the work keeps on going. Like you can leave home and work keeps on keeping on. I've been doing that for like 30 years. In combination, especially if you have a good laptop, then you can have best of the both worlds.
It’s not that what I do can’t fit on a laptop, but rather that I prefer to minimize weight in the machines I travel with, and if I need power while I’m out there’s always macOS’ built in remote desktop capabilities which work quite nicely with Tailscale.
So if I’m going to have a machine always sitting on my desk at home anyway, it may as well be a desktop with fewer compromises and no battery to slowly degrade while never getting used.
A nice bonus is that it takes a lot more to make the fans on a desktop noisy relative to what it takes on an MBP, and if there’s one thing I dislike about computers it’s fan noise.
I feel like in 2026 maybe they realized that "pro" users (engineers, designers) mostly just want laptops + external monitors anyway. The Apple Silicon CPUs are so f'ing good, the % of people who need an uber-desktop is smaller than ever.
24" is a good size for casual users which is the main market. You can have two roomy-ish GUI apps (two web pages, etc) side by side.
How is it that after 10 years of Apple releases, people are still complaining about it "missing" feature X? Not having every checkbox ticked is Apple's way of having shiny new releases all year round.
The M6 Pro and Max variants with higher memory support have been dropped in favor of accelerating M7.
This has been reported for many months. Sorry if you missed the news, but if you need a much higher memory variant the M5 Pro/Max are what’s available this cycle.
I understand that, but they said they were waiting for a higher memory variant M6, which was not planned. If they need higher RAM they can go M5 Pro/Max (outside of iMac form factor) or wait hopefully for newer iMac Pro variants in the future.
To be honest, I doubt we're going to see iMacs with very high RAM any time soon. RAM is expensive and most people buying high-RAM machines want to bring their own monitor, not get an all-in-one with a small-ish screen.
Lowest spec config costs £1529 vs £899 for the equivalent Mac mini, but the mini gives you Ethernet and 2 cores. Highest spec goes up to £3099 vs £2299 for a matching mini.
£700/£800 buys you a 24" display (with an unspecified refresh rate, so presumably 60Hz), a keyboard, and a mouse. I loved my 27" iMac to pieces, but it's really hard to justify buying this thing today.
That's about $1000, and it buys you a 32" 4K OLED panel with a high refresh rate, better than anything the Mac has. That's the kind of monitor you would pair with a gaming rig though, and probably overkill for the kind of office use the Mac is intended for.
I wonder why the iMac still has that chin design and small panel. They’ve been producing displays for long enough that the iMac and Studio Display should have the same form factor.
There may be some technical reasons for it, but I'm not convinced. The chin is a core part of the imac design language. Without the chin it would just be a display and not recognizably different from any other display. The chin is part of the design that that makes it recognizably an imac.
The chin is where Apple puts the logic board and speakers for the iMac. Yes, they could move that behind the display, but I'm guessing that'd make the display thicker (which they wouldn't want) and make the thermals harder. It's certainly something they could engineer, after all the iPad has its logic board behind the display. But it's not like the chin serves no purpose and it probably helps with the thermals and sustained performance and probably makes it easier to engineer everything for what is probably one of their lower volume sellers (compared to iPhones, iPads, MacBooks).
I worked for an AASP in the early 00s and I questioned this, considering that previously the logic boards were actually housed behind the display for both PowerPC and Intel models[0]. This does appear to be mostly true[1] (some of the logic board pokes up beyond the chin).
The white plastic iMacs from the PPC and early Intel era were about four times thicker than the current design. Back then they were putting optical drives and 3.5" hard drives and AC power supplies behind the display; now, it's too thin to fit an Ethernet port. The current set of tradeoffs really doesn't make sense to me, but if you accept the thin design as a constraint the continued existence of the chin is pretty obviously necessary; those older iMacs could have much more easily ditched the chin.
It'd be interesting if they used that power brick tether to drive the display similar to the Samsung Frame, which takes power and signal from a fiber optic cable that runs really easily in a wall. If they could shuttle Ethernet up the power cord, they could send video signal back, too.
The colours are a nice touch though I wish they’d bring back a little more whimsy into the designs. These things are obviously more display piece than workhorses now with all that flamboyant colouring, so go all out? Maybe give it a larger border radius, or made the rear end rounder. Oh heck, make the entire screen round even! Bring back the puck mouse and make a puck keyboard!
I love the magic mouse, had one going since 2016 and it is still great. Not a fan of their keyboards but the swipe + scrolling exp. on the magic mouse is great IMO.
The Magic Trackpad is a far better pointing device (partly because the OS is so trackpad-focused, partly due to the Mouse's poor/outdated hardware). I'm surprised Apple still isn't pushing it as the "standard."
The iMac continues to be an aesthetically pleasing machine I sorely want for my space, yet one I cannot justify because of its anemic innards relative to my desired use cases.
It’s just a really good looking computer, especially with the accessories. Give me one with an M6 Pro and a 128GB memory cap, and they can take my money as I move my homelab and AI compute onto it.
> Just like Intel not shipping ECC for client SKUs when DDR5 design makes it really necessary
The ECC in DDR5 is on-die ECC and that's not "real" ECC, it's what DDR5 needs to not fail. Side-band ECC is the standard method, employing extra memory chips and 72bit memory. OEMs mix these in the marketing materials to fool the users into thinking they buy the better option.
Yes, here I'm referring to actual ECC, not the on-die ECC. All DDR5 chips have on-die ECC as a prerequisite just to reach error levels comparable to standard non-ECC DDR4, but from a hardware analysis perspective, even with the on-die ECC, DDR5 still needs ECC more than DDR4 (which already needed it).
I read similar reports so many times, when I got my 165hz screen I got disappointed. I also disable it on my phone to get more battery life. Different folks, different strokes.
I switch between a variety of displays throughout my day, ranging from 60hz up through 240hz and yes there’s an obvious visual difference, but I adapt to it in a matter of seconds.
It’s nice for games but I don’t really care for productivity use. In fact in that situation I’d take integer-scaled HiDPI density over refresh rate in that scenario.
How many watts are you saving with that, realistically? If that few minutes of extra battery is a game changer, you need a bigger battery, not a worse screen.
I have a 60hz monitor and a 144hz monitor and I simply can't tell the difference in normal usage. I can see a difference on something like http://testufo.com if I specifically look for it, and until I checked that I assumed the OS was just lying to me and the monitor was actually set to 60hz.
They are very popular amongst the elderly. Well specifically those of us setting the elderly up with a computer.
Mechanically straightforward since it’s all in one. Pretty much just the power cable, keyboard and mouse. Pretty unbreakable ux wise, reliably sleeps with little power draw and wakes up quickly without them questioning if it’s broken. Reasonably unobtrusive updates so they don’t go turning them off. Etc.
Popular with people who want to give a kid a computer between elementary and high school age, does everything a kid needs. With the bonus of not having to worry about your kid wasting time playing games.
Yup. My 80-year-old father is replacing his Intel iMac with one of these tomorrow. (photo editing, 3D design for printing)
We thought long and hard about a Mac Mini — and not happy about going from 27" to 24" — but a Studio Display doubles the price and he's not willing to take another chance on third-party stuff.
The maximum of 32 GB RAM has to be a joke. My Linux laptop has more RAM, more SSD, more CPU at the same price, and it can run games on top of that. Hard pass, even if I were to tolerate the OS.
I still think those expensive Apple monitors (which even had RAM) were intended to be 'iMac Pros,' but due to stagnant growth in the all-in-one market, they never saw the light of day.
But they aren't Apple.
2. Aesthetic
3. Pretty colors
4. Nostalgia
24” or even 27” feels like such a downgrade.
Also please make the iMacs usable as external monitors agains. Would buy one as a “livingroom computer” instantly if it was also possible to occasionally use it as a docking station for an air..
[0] https://www.retinarelay.com/
Would just be nice if I could buy the monitors from apple too.
iPad docking station too
The generation doesn't mater as much to me as the memory bandwidth. When that day comes, I'd rather have a M1 Max 64GB over a M5 Pro 64GB.
And now if you stretch you can run DeepSeek Flash 4.1.
And if you were willing to roll up your sleeves you could build your own AI lab at home and run this model and models like GLM Flash 5.3 and DeepSeek Flash V4.1 at lower quants. The budget GPUs (like V100) are kind of not budget now, but still <5K to acquire 128GB of fast VRAM that can compete with a 5090 and actually has a lot more interesting options available IMO.
I asked Claude to come up with 7 problems to solve that were not part of any benchmarks. Besides speed, I asked it to put together a scoring that would reflect models that perform well on the 7 problems and in a reasonable time-frame (RWS, the definition is in the artifact). I valued models that produced good answers in a reasonable time better than models that had very high throughput but kept spitting useless stuff. Overall, IIRC most of them still had a >30% chance of producing wrong/non-working replies.
I then tested Strata ( https://github.com/niko1221/strata ) and the results are not even close. You can basically ignore everything in that table and use Strata instead, you can use bigger/less-quantized models and have way better results. Basically any otherwise-decent model degrades noticeably at Q < 5, and KV cache at Q4 also contributes a lot.
Still, a 20$/mo Claude subscription is way cheaper/more efficient if you code 2-3h in the evening than running stuff locally, unless you really have hardware than can hold models that get most things right at the first try. You can iterate way faster and cover a lot more ground in 2-3h using a Claude subscription, or OpenRouter if you prefer to change models. You get faster replies that are 99% correct at the first try, whereas using the local model you'd be spending 30% of your time fixing things that don't work and prompting it to do better.
Nowadays I use the local model to delegate tasks that would burn a lot of tokens, like sifting through big data archives for indexing and such.
It will show you on the model selection IF a model fits and if you use a "Qwen 3.8-35B-A3B" type of model, it should just work out of the box. A3B stands for Active which means you need a lot less fast ram.
You will run into issues fast though: If you have big tasks for it to do, your pc/mac will get warm very fast and noisy and you will cosume relevant more energy.
And as you mention: yeah small context!
Its still not that practical in my opinion.
Dense models also don't like quantization as much and are less tolerant of it. There are some very interesting smaller models like https://huggingface.co/nvidia/NVIDIA-Nemotron-Labs-Dory1.0-4... Dory that I would check out. You need system RAM or to stream a larger MoE model from disk and it won't be fast. You need to specialize the models some to get quality results if you have very limited system resources.
https://github.com/Niko1221/Strata/
My setup is a Ryzen 3600, 90GB DDR4 allocated to a VM (don’t even really need that much, just had it available, special thanks to the year 2024), and an RX 9060XT 16GB ($500 GPU).
I get around 40-60 tok/s depending on the quantization level I choose.
As you can see, the CPU is nothing special, don’t even need DDR5.
So it depends on what you're doing. Using it for a fun oracle without feeding it too much context per turn? Sure, an older Max chip is great.
As a coding agent doing meaningful work on a sizable project? Compared to a cheap as chips cloud option, it will take an order of magnitude more time to complete.
Isn't it also rumored that the M7 is reworked for AI?
And Xiaomi announced their AI Cube with 1.2t of bandwidth. Just because Nvidia is protecting its business by giving consumers either compute or bandwidth and Apple being something in between, doesn't mean we can't get both a lot better balanced.
I'm gonna max out most of the specs on the next one I get, would feel insanely wasteful to do that now.
I don't know man?
The generation kind of does matter. I'm not gonna lie, matrix multiplication units speed things up considerably. That hardware confers a material change in capability.
Maybe from M5 up, it doesn't matter? But you're definitely going to notice the difference between M1 and M5 for instance.
I am one of those: bought the M1 Max with 64gb thinking in running VMs, afterward bought a lighter Air with less memory and ended up using the M1 Max as a kind of luxury for LLMs and multicore computing.
The only hope we have is the AI bubble bursting, but that will undoubtedly come with its own set of macroeconomic surprises.
The fabs are terrified to overscale in case the market collapses before the builds are complete.
> AI datacenter provisioning will go down
Depends on political opposition at both local and national levels. Hard to predict the future, which feeds into the previous point.
It feels just as fast as day 1 and I've never had any speed issues. Say what you want about Apple and their pricing and ecosystem but I've been using their hardware for over 20 years now and it's always been top notch.
If you buy their support/AppleCare, your support and warranty is excellent too. They don't skimp. I've seen them go so far past the extra mile it's unreal.
Definitely grabbing 128 GB + for the next machine.
I jest...but I'm disgusted by the price gouging going on. Glad my hardware is relatively recent and I had mostly maxed out already when I bought it a few years back. The same setup today would be closer to $7k with equivalent parts.
It only makes sense for niche use cases, like your grandpa who is happy to have a single spot in his home for the computer, or a reception desk at a business, etc.
This is basically 99% of the proposition of the iMac at this point. If you don't need the specific all-in-one, color, and other design aspects of the iMac or can afford a Studio display, there's no reason not to buy some other display + a Mac mini or a laptop + display
Though I have had good results buying 1-2 generation old refurbished Macs as my secondary machines or for family members who don’t need cutting edge everything.
It’s even more valuable now that Apple silicon of every generation is more than enough to run every non-power user use case short of newer video games.
I'm surprised they haven't yet gone the route of making a hyper thin screen and hiding the actual cpu somewhere else (something akin tot he puck for the Apple Vision display). Hell you could probably do a proprietary wireless signal and have the display be completely detached. (Or existing wifi6 or something?)
The edges of the thin monitor could be actual transparent glass.
On a desktop you view face on, who fucking cares how thin it is?
"And we’re just getting started."
It is an Apple machine, yes.
It’s too bad. A high end iMac still holds a lot of appeal, especially for those seeking clean desk setups. I’m using an MBP hooked up to dual monitors through a dock right now and it’s fine, but I do miss how clean my desk was back when it was a VESA mounted iMac Pro and companion monitor.
I’ve kept that philosophy over the years, the MBA was replaced by the 2017 12” retina MacBook and then again with the 13” M2 MBA. The Mini gave way to the 2018 Mini, then a M1 Max Studio. I even attempted replacing the MacBook with an iPad though that didn’t really workout.
It’s the best of both worlds really, enough power to do everything when on the go and even more power back at the office.
0: https://elliotjaystocks.com/blog/a-note-about-my-new-mac-set...
What's the appeal there? Doing big-RAM-requirement stuff that just won't run on a laptop?
Nowadays, the M series chips are so powerful that I’ve not had a real need to use my Studio and work mainly using my M2 Air.
So if I’m going to have a machine always sitting on my desk at home anyway, it may as well be a desktop with fewer compromises and no battery to slowly degrade while never getting used.
A nice bonus is that it takes a lot more to make the fans on a desktop noisy relative to what it takes on an MBP, and if there’s one thing I dislike about computers it’s fan noise.
24" is a good size for casual users which is the main market. You can have two roomy-ish GUI apps (two web pages, etc) side by side.
If it were back to 27" and hidpi screen again it might make sense
Sam predicted price-per-transistor-per-square-inch density would asymptote, while Leslie predicted it would level off and then regress.
Leslie's Law is in full effect, it seems.
This has been reported for many months. Sorry if you missed the news, but if you need a much higher memory variant the M5 Pro/Max are what’s available this cycle.
To be honest, I doubt we're going to see iMacs with very high RAM any time soon. RAM is expensive and most people buying high-RAM machines want to bring their own monitor, not get an all-in-one with a small-ish screen.
Peripherals not included.
I would love to have a pink one for my MBP!
Or at least give us the option for a black display surround. The white bezel around the display is such an eyesore...
£700/£800 buys you a 24" display (with an unspecified refresh rate, so presumably 60Hz), a keyboard, and a mouse. I loved my 27" iMac to pieces, but it's really hard to justify buying this thing today.
That's about $1000, and it buys you a 32" 4K OLED panel with a high refresh rate, better than anything the Mac has. That's the kind of monitor you would pair with a gaming rig though, and probably overkill for the kind of office use the Mac is intended for.
0: https://www.ifixit.com/Teardown/iMac+Intel+27-Inch+EMC+2309+...
1: https://www.ifixit.com/Teardown/iMac+M3+24-Inch+Teardown:+Ap...
I used to put post-its on mine too.
https://www.apple.com/shop/product/mxk53am/a/magic-mouse-usb...
It’s just a really good looking computer, especially with the accessories. Give me one with an M6 Pro and a 128GB memory cap, and they can take my money as I move my homelab and AI compute onto it.
The ECC in DDR5 is on-die ECC and that's not "real" ECC, it's what DDR5 needs to not fail. Side-band ECC is the standard method, employing extra memory chips and 72bit memory. OEMs mix these in the marketing materials to fool the users into thinking they buy the better option.
Her eyes were much less tired at the end of the day.
It’s nice for games but I don’t really care for productivity use. In fact in that situation I’d take integer-scaled HiDPI density over refresh rate in that scenario.
Would have bought one otherwise.
Mechanically straightforward since it’s all in one. Pretty much just the power cable, keyboard and mouse. Pretty unbreakable ux wise, reliably sleeps with little power draw and wakes up quickly without them questioning if it’s broken. Reasonably unobtrusive updates so they don’t go turning them off. Etc.
We thought long and hard about a Mac Mini — and not happy about going from 27" to 24" — but a Studio Display doubles the price and he's not willing to take another chance on third-party stuff.