22 comments

  • joshstrange 1 hour ago
    Due to pricing insanity (not that Apple prices weren’t insane before the ram/ssd shortages) I’m not in the market but I do wonder if my next computer should be a Mac Studio instead of a MBP that lives its life docked. Might be better to just run a Studio and Neo for the very few times I actually need remote capabilities.
    • sanderjd 0 minutes ago
      Yep, this is my exact thought. The pendulum has swung back toward a desktop making more sense for me than a laptop. It all depends on whether there is anything useful to do with an amount of computation that can't be fit into a laptop package. For a long time there wasn't, now there is.
    • PaulRobinson 30 minutes ago
      I've been thinking about this a fair bit recently.

      We make a lot of price/performance compromises for having an attached screen and keyboard on our computer. That was what got me started.

      Then I remembered the days of having to go to a special corner of the house to use a computer, vs now when I have a computer with me all the time. In my bag, on the sofa, on the train. Hell, I'm writing this on the work MBP while waiting for an appointment.

      And you know what, I think I got more done when I went and sat in a corner of the house all those years ago. I set up an area for "computer work", and it worked really well.

      I have a home office, but it's a jumble of cables going into docking stations and all sorts of weird stuff. I think if I streamline it and turn it into a proper "computer room", I might get some of that mojo back. I might even convince my partner that surrendering the home office and having a corner of the den might be good - she can watch TV while I tinker. And I won't be balancing a laptop on my knee and trying to do two things at once.

      And the price/performance thing comes back in. Hmm.

      • simgt 4 minutes ago
        I've done that, but I chose a Framework Desktop instead. The latest Fedora is closer to Snow Leopard than anything Apple has to offer. Downside is that I still have my MBP because of the lock-in and occasionally pick it up to do computer stuff in weird places.
      • AshleyGrant 5 minutes ago
        There is a definite mental aspect for most WFH folks to having a space that is dedicated to work. I'm not unique in saying this, but the way I put it is "If you work from anywhere in your house, then you're always at work."

        And that, from mental load standpoint, is not healthy for most folks.

    • bearjaws 2 minutes ago
      Recently took a Minisforum 7840hs PC out of rotation as a media PC and made it a full time coding workstation with Proxmox. I do a VM per project due to the nature of agentic editors.

      I was using a VM setup on my MBP but it felt like a huge waste, having to leave a laptop on 24/7 when all it did was run Claude Code inside VMs.

      I likely will stick with a Macbook Air 15" for next purchase, and beef up my "Claude Server" down the road.

    • hectdev 43 minutes ago
      I dusted of my lightest computer with an M1 chip and use Tailscale to make my network virtual from anywhere. Been running a. Pi5 as a main house hub and an M1 Pro as an always on Mac. It would be nice to go all out and make a Studio a hub I can just screen share into for major compute.
    • appplication 1 hour ago
      I had the same thought, I grabbed a studio two years ago for this reason and it’s been great. 99% of the time lack of portability isn’t a concern. Every now and then (e.g. travel) I notice the limitation, but it’s not much of an inconvenience to just not do some work for a bit.
      • Gareth321 54 minutes ago
        Plus remote work is getting easier and easier. There are so few instances when I'm not able to get online. If we lived in a world where hardware were getting cheaper, it might make sense to splurge. In this environment I think the Neo is perfect.
        • dannyw 36 minutes ago
          Build quality of the Neo is extremely good, I love the keyboard — it’s more tactile and reminds me of early 2010s MacBooks.

          I’ll be selling my M4 MBA soon, I genuinely use the Neo more. Huge difference in typing experience.

          Great repairability is a plus. It was super easy, and actually fun to open. Felt like unboxing an Apple product. Applied the thermal paste mod for $10 which works excellently; I’ve had it shortly after launch.

          And I love the notchless display, even if I wished the color gamut was a bit better.

    • ThouYS 25 minutes ago
      Having replaced my MacBook with a Mac Mini, I would reconsider. The MacBook is just such a _complete_ package. Great speakers, great keyboard, fantastic screen, the fingerprint sensor thingy.. Takes a lot of gear to match that
      • cj 20 minutes ago
        If your computer never leaves your desk, the iMac is pretty competitive with those features. Even comes with a TouchID keyboard.
        • mikestew 9 minutes ago
          I’ve had iMacs for almost 20 years. My last one was indeed my last. Without target display mode (use the Mac as a monitor), I’m ditching a perfectly good monitor. I was going to buy a Mac Studio and a good monitor to replace the iMac until the spouse reminded me that we are now retired and will spend time in a camper. So a MBP for me, but others might do well to consider a Mac Mini/Studio.

          iMacs are great for a lot of use cases, but my image of the typical HN user would prefer to keep the monitor separate.

      • pebble 17 minutes ago
        Not an option if you're trying to drive 3 decent screens.
    • jermaustin1 1 hour ago
      I've been holding out, because I think my next purchase will be a Studio with an Ultra Chip in it. I'm wanting it to be a "forever" server, so I'm holding out while I can.
      • Gareth321 52 minutes ago
        Supply rumours are next year we see an M7 AI-focused chip with large inference performance upgrades. It's unlikely we'll see heavy upgrades in other areas. If you care about AI, it's worth waiting. If you don't, pull the trigger now. RAM constraints are likely to get worse next year. Or wait 2-3 years and prices should be back to Earth (plus newer and even better chips).

        I'm waiting this out.

      • jubilanti 54 minutes ago
        Then you'll always be waiting, there's always something new the industry tries to tempt you with.
        • jermaustin1 9 minutes ago
          I just wait for a cycle or two where the leaps and bounds are more like hops and steps. So if the M7 Ultra improves inference by 2x over the M5, but the M9 Ultra only improves by 1.2x over the M7, that's my signal to buy. Unfortunately they haven't slowed down yet.
      • simonh 57 minutes ago
        Buy in 2 years, or buy now and have it last 2 years less than forever.
    • armadyl 27 minutes ago
      That’s nearly what I do but on a smaller scale. My iPad Pro serves as my laptop 90% of the time, and the 10% of the time I need to actually code and test in a chromium browser I remote into a mini.
    • jgwil2 39 minutes ago
      If all you want to do is remote into your desktop, Neo seems like overkill. Why not just get a $200 Chromebook and save yourself $500?
      • rjrjrjrj 23 minutes ago
        Because the screen, keyboard, and especially trackpad on a $200 Chromebook sucks?
        • bredren 19 minutes ago
          Also: the enclosure, and the hinges.
    • epolanski 10 minutes ago
      For a desktop you may find yourself better on a Linux or Windows machine price/performance wise.

      I personally own an M3 ultra, an M1 max as laptops, but my desktop is a Ryzen desktop I built in 2022 and it was a third in price of the ultra for more power.

    • ape4 1 hour ago
      How about business where you send in all your old devices and get back a SSD using using their memories
    • hirvi74 42 minutes ago
      Do it! I went with the Mini/Neo combo. I don't need MBP power when out and about. When at home, the Mini is all I use.
    • super_mario 1 hour ago
      I was in the same situation, I used maxed out 15'' M3 Max MacBook Pro docked to Studio Display closed on vertical stand behind the screen. It was fine for office work, but running local LLMs would definitely overheat it. The battery started degrading purely due to heat issues. And it was audible as well.

      I decided to get Mac Studio M4 Max, also all maxed out config and the cooling is so much better that I can run local LLMs like Gemma 3/4, gpt-oss 120b all day long without any heat issues or any audible fan noise. So for my use case it was the right decision. I subsequently added 15'' M5 Max MacBook Pro all maxed out to my collection and even though it is slightly faster on LLM inference (I get 100 tokens/s with Gemma 4 27b model), you just can't run LLMs longer than a few minutes. It starts overheating and gets really loud.

    • tamimio 1 hour ago
      That’s what I have been doing for years, it remains in the house secured while I ssh into it from an old thinkpad. You can get air to pair it with it if you really wanna have that seamless flow, otherwise, ssh works well.
    • try-working 54 minutes ago
      Laptops can't do agentic engineering. They get hot as hell and battery drains instantly. I think this will promote a switch to desktops for the next couple of years, until we have new mobile chips.
      • steve1977 49 minutes ago
        But laptops can remote into boxes that can run agents.

        So a combination of a powerful desktop and a "cheap" laptop might indeed be attractive.

      • jonathanberger 41 minutes ago
        Are you referring specifically to agentic engineering with locally hosted models?
    • code-blooded 20 minutes ago
      I'm thinking the same, except I'd never go Apple again. I am planning to get a regular, modular mATX desktop (+Linux) for vast majority of my computing needs and strongly prioritize focused work at my desk.

      It's (relatively) cheap, powerful and as problem-free as it gets.

      • SubiculumCode 12 minutes ago
        I can't wait for an actual competitor to the M chips from apple. It's frustrating.
      • swozey 13 minutes ago
        I'd never go x86 again after owning an m1, and I have a, I guess now, $5k+ 7900x + 4090 sitting next to my 7 year old mbp that I would have had to replace with 2-3 x86 laptops by now
  • blints 1 hour ago
    10 grand for 256GB memory. Likely double that for 512GB, but won't be available or finalized until October. Thunderbolt 5 is highest bandwidth external IO available at 120Gb/s. 1.2TB/s claimed max internal memory bandwidth.

    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.

    • BugsJustFindMe 1 hour ago
      > Not exactly "future proof"

      Computers are never "future proof".

      • mannanj 8 minutes ago
        About 20 years ago my dad bought me a $5k computer, it was future proof for about "5 years" before we had to upgrade its internal parts (more memory, new graphics card).

        It was future proof but not really because it struggled a lot in its final years.

      • mschuster91 46 minutes ago
        > 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.

        • jve 4 minutes ago
          Think it would have same memory bandwidth if the RAM was upgradeable?

          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.

          https://news.ycombinator.com/item?id=49041256#49082206

        • mhast 8 minutes ago
          The main PCB is pretty much everything that has value. The rest is a heatsink, case and PSU.
        • _kush 26 minutes ago
          If it was upgradable, then yes, spending more on top of it every year would make it future proof, but that's not the point. It's that spending 10 grand doesn't get you a future proof computer today.
        • fearmerchant 24 minutes ago
          The way the Apple M-series does ram that might be difficult to pull off.
          • mschuster91 20 minutes ago
            > The way the Apple M-series does ram that might be difficult to pull off.

            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.

    • dist-epoch 1 hour ago
      > 10 grand for 256GB memory.

      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.

      • blints 51 minutes ago
        The relevant comparison isn't one mac studio to one RTX 6000, it's a 24 channel DDR5 system, which also has ~1.2TB/s of memory bandwidth (or more when Xeon 6 compatible 8800mt/s memory becomes widely available), vastly higher prefill due to more CPU horsepower, orders of magnitude faster networking, can hook into GPU accelerators, can be upgraded etc. A baseline 384GB system from eg Puget is ~30K vs ~12K for the 256GB Mac Studio and you do get value for the money.
        • ricardobeat 3 minutes ago
          So 3x more, plus the cost of a GPU (another 10k?). How is that value for money to get slightly better performance?
      • petercooper 55 minutes ago
        How's the compute side now, I wonder? Because while the Ultras have impressive memory bandwidth for inference, processing prompts still takes a dog's age on my M3 Ultra. I heard the M5 makes some strides forward in this area, though, and the M7 in particular promises to go a lot further.
        • dannyw 26 minutes ago
          M5 is excellent, they’ve finally gotten their own tensor cores.

          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.

      • angoragoats 57 minutes ago
        Except the RTX 6000 will run circles around the Mac studio in just about every way. Memory bandwidth is literally the only spec where Apple is competitive, and while high memory bandwidth is necessary for LLMs to perform well, many people strangely don't understand that memory bandwidth alone is not sufficient.
        • F7F7F7 43 minutes ago
          It better because you’ll need a few of them to run some larger models (I’ll be just as vague citing which models).
    • cma 1 hour ago
      3 of those thunderbolt 5 ports, so you can do a fully connected 4 machine cluster topology.
      • blints 58 minutes ago
        It's unclear to me how bandwidth scales with multiple connections. Many-to-many does not seem ideal. Daisy chaining would be fine for straight pipeline work. There doesn't seem to be an equivalent of a ethernet switch for thunderbolt 5 though.
  • alberth 1 hour ago
    It looks like speculation that Apple would raise the base chip’s maximum RAM from 32GB to 48GB was wrong.

    Apple also launched the base M6 today with a 32GB RAM limit, suggesting 512GB may remain the maximum for Ultra chips for some time. Since these Ultra chips combine 16 base chips:

    32GB × 16 = 512GB

    • dannyw 3 minutes ago
      They probably literally don't have enough NAND to go around. 768GB of memory (48GB x 16) is enough for nearly 100 iPhone 17s; that's $800k of iPhones at MSRP, although likely much lower margins than these high-RAM boxes.
  • egonschiele 1 hour ago
    > M6 supports up to 32GB of unified memory to multitask across demanding apps and run LLMs on device for secure and private agentic tasks. It also provides up to 170GB/s of unified memory bandwidth — a 10 percent increase over M5 and a 2.5x increase over M1.

    Isn't 170GB/s slow for bandwidth?

    • blints 1 hour ago
      It is. That's the mac mini. For local LLMs you would want the Mac Studio, which tops out at 1.2TB/s.
    • matja 1 hour ago
      It's higher bandwidth than any dual-channel DDR5 desktop machine, but Apple never quote the memory latency, so hard to compare otherwise.
    • mkesper 1 hour ago
      For max memory bandwidth you need to buy the Ultra versions (M5 Ultra: 1,2TB/s, this gets comparable to real GPUs regarding the memory bandwidth).
    • scosman 1 hour ago
      It's fast by computer standards and excellent for entry level chip. The Pro/Max/Ultra chips are always faster.

      Compared to something like VRAM it's slow.

    • kamranjon 59 minutes ago
      You would want to get the M5 pro version with 307gb/s if you were interested in running local LLMs.
    • tristor 1 hour ago
      Kinda. Strix Halo does 256GB/s of memory bandwidth, and is significantly slower than an M5 Max (614GB/s). Feels like intentional market segmentation?
      • kamranjon 1 hour ago
        You can get the m5 pro in the Mac mini with 307GB/s at 64gb of memory it’s $2899
  • meerita 1 hour ago
    Mac Studio with M5 Max starts at $2,499 (U.S.) and $2,299 (U.S.) for education. Additional configure-to-order options are available at apple.com/mac-studio. Mac Studio with M5 Ultra starts at $5,499 (U.S.) and $5,099 (U.S.).

    I am in Europe, and the Mac Studio M5 Ultra GPU 64 cores with 96GB RAM is up to 6.649,00 €. Ouch.

    • nine_k 1 hour ago
      To put this into a perspective, Google helpfully reminds:

      > A fully configured IBM Personal Computer AT (Model 5170) with expanded memory and storage cost around $5,795 to $6,000 at its launch in August 1984, which equals roughly $18,600 to $19,300 in 2026 USD.

      • mrala 50 minutes ago
        It would be interesting to compare the costs of a top of the line machine every decade or so. Costs were steadily decreasing until recently.
        • jacobr1 27 minutes ago
          They still are, if what you want is roughly the same as the prior generations capability with some uplift (making then number up, but say 20% faster or more ram or whatever).

          What is changing is that there genuine demand for more capabilities disproportionate to the cost decrease curve. Fab demand and supply constraints have slowed or even reversed some cost decreases - but that is still getting absorbed by the overall systems costs when you are looking at things like laptops. If you all you want is the last decades demand to browse the web and use office - things are cheaper than ever.

    • alfanick 1 hour ago
      Don't forget that US prices usually do not include the VAT, while EU prices usually do include respective VAT.
  • intrasight 1 hour ago
    It seems super reasonably priced to me. It's only twice as expensive as my first Mac which only had 128K of memory.
    • epolanski 5 minutes ago
      Base models are okay-ish.

      But +4000$ for an additional 128GB of ram is simply milking the customers, as they know they will have many of them.

    • tiahura 36 minutes ago
      That came with a monitor and floppy drive.
      • varispeed 19 minutes ago
        and this one comes without a floppy drive.
  • prometheus1992 10 minutes ago
    The new mac minis and mac studios are going to be in shortage for at least first 6 months from 9.22
  • gizajob 1 hour ago
    Bizarre there isn’t a 1TB RAM option hidden away for the excessively frivolous or VC funded.
    • gauntr 1 hour ago
      Same reason they cut the big options on the existing models, this way they can sell more devices. The additional cost for the additional 512GB would have to make up for the loss of another sold device otherwise. No idea if there would really be that many people buying this then while on the other hand AI stuff makes people do crazy stuff, so...yeah :)
      • MisterPea 10 minutes ago
        Considering Apple pricing it actually might.

        256GB model is $10k and the 512GB version will probably be double

    • petercooper 1 hour ago
      They seem to be suffering from the supply constraints like everyone else. They phased out the higher capacities on the M3 Ultra Mac Studio a while ago, and if you order a 128GB MBP, say, you're looking at six weeks or more for delivery.
    • varispeed 18 minutes ago
      It's more bizarre that Apple got caught with pants down. Focused on CPUs and ignored RAM.

      Seems like miscalculation. If they had their own fab for RAM, they could completely corner the market today.

      • mlsu 1 minute ago
        They don’t have their own fab for CPUs either.
      • xdertz 5 minutes ago
        They have no fab for CPUs, they are manufactured by Samsung and TSMC. The bottleneck is in manufacturing RAM not CPUs so there is nothing Apple can do here.
      • actionfromafar 0 minutes ago
        They would have had to start building that fab 5-10 years ago. It would have been incredible foresight to do so and it would have looked insane.
  • speckx 52 minutes ago
    I was looking forward and hoping that the Mini and Studio would have 8K at 120Hz. Oh well, maybe the M7s will have that.
  • nalekberov 11 minutes ago
    Boy, oh boy Apple is the new shovel seller during AI gold rush.

    Most people at Apple have already realized that their processors are already too powerful for regular users - heck, as a developer my M2 Pro with 32 GB RAM is more than enough for me.

    Regular users don’t care about local AI either. So, they will probably extract as much money as possible during AI gold rush, but then we will most likely see Apple

    a. Making their software worse (god forbid, forced updates)

    b. Making their hardware impossible to repair (as they almost accomplished this already) and easier to break.

    • dannyw 8 minutes ago
      I dunno, Apple's been throwing many bones to their customers who use their Macs for AI stuff; like Apple working with, and signing TinyGPU's NVIDIA eGPU drivers.

      Plus introducing features like RDMA over thunderbolt, which is critical for distributed inference/training/etc. On the software side, Apple is investing heaps.

      It's still ridiculous they don't support expandable NVMes, but the memory being soldered makes sense, you need it for 1.2TB/s bandwidth.

      They are still selling high-margin hardware. Apple loves selling high-margin hardware.

  • alberth 1 hour ago
    M6 (base) in Mac Mini too:

    https://www.apple.com/mac-mini/

  • swader999 42 minutes ago
    Here's me trying to justify this when I can run frontier models in the cloud for less than the monthly finance charge for this beast.
    • dannyw 31 minutes ago
      If you like to experiment with training / finetuning / etc on LLMs, these are actually incredibly ‘cheap’.

      1.2TB/s memory bandwidth unlocks a lot with 256GB unified, and agentic AI is pretty good at optimising performance.

      For comparison, to get 256GB with NVIDIA, you’re looking at a DIY workstation build (need pcie lanes), and like $70k?

      The spark’s ~250gb/s bandwidth doesn’t really count here.

      • ComputerGuru 9 minutes ago
        Neither is the right alternative to compare to. You aren’t going to hit 100% utilization (if you are, ignore me, this doesn’t some to you, and write a blogpost for me to read and share).

        The comparison should be against renting in the cloud for the duration of your task for training and research or using pay-per-api-call providers for general inference instead of buying your own hardware (and paying the electricity and cooling bills on top), because let’s face it, the models you want to use are probably the same ones available on inference providers (but, yes, some are more trustworthy than others).

        Speaking as someone that does ML/AI research, you are essentially paying a huge premium for being able to just run your Python script at any time without setting up a deployment script and harness to run the job remotely, while your hardware sits essentially idle the rest of the time.

        The only way to make the math work is if you rent your hardware in the background for inference while you’re not using it in anger, but despite all the startups and promises that has never become as streamlined as mining bitcoins or shitcoins used to be and they don’t pay out as much as they say they would. Renting your hardware for training is another option but doing that is a lot more involved, options are fewer and farther in between, you won’t get as much utilization out of it, and doesn’t let you feasibly abort running tasks at a moment’s notice.

      • Zylokloto 20 minutes ago
        To experiment, its still al ot cheaper to prepare everything locally and then just rent a GPU Node on all of these non hyperscalers.

        1-2$ / hour.

        I'm not regretting my setup at home as it got paid by my company which makes sense here, but paying for electricity is quite high and makes already 0.3$/hour alone.

        I would argue, the most interesting use case for running it at home is some personal agent which you want to run 24/7.

      • MisterPea 8 minutes ago
        Yeah not really lol.

        Only reason to buy this if you want to own your compute.

        Experimentation and inference are all going to be cheaper on the cloud

  • ricardobayes 1 hour ago
    512GB unified RAM is going to be really good for running local LLMs.
    • tarr11 1 hour ago
      What is unified ram? RAM and VRAM as one thing?
      • Zylokloto 19 minutes ago
        In best case its also on-chip high speed ram.
      • AbsurdCensor 1 hour ago
        Big ole pool of very fast ram that can be accessed by the CPU and GPU. Lets you run larger models. AMD does the same thing with Strix Halo. I have a 128gb machine at home, and have had difficulties running 120b models, but 70b and below run pretty well.
      • lynndotpy 1 hour ago
        Yep, exactly. It's just one shared pool of RAM with zero-copies necessary.
  • nythroaway048 1 hour ago
    512GB unified memory option coming available in October.
    • marcuskaz 1 hour ago
      The 256GB option is +$4,000 - the overall price for 512GB setup would probably be $20k!
      • notnullorvoid 38 minutes ago
        It needs to be a little less than double the overall price for 256GB option, otherwise it's better to get 2 256GB and link them.
        • Zylokloto 18 minutes ago
          you can't link onchip memory.
  • polyterative 56 minutes ago
    Very much happy with my machine.Got a base m4 max studio in December. 2350eur what a deal
    • TechSquidTV 52 minutes ago
      I only with I got more than 96GB at the time.
  • neko_ranger 47 minutes ago
    No looking to cheat, which is better: the MAX or ULTRA?
    • baggachipz 43 minutes ago
      Depends if it's Pro Ultra Max, or Plus Max Ultra.
  • tristor 1 hour ago
    I wish they were offering 1TB of Unified Memory for the M5 Ultra. I already have an M5 Max MBP w/ 128GB of RAM for running local models, and while there's a /few/ models that I can run in 512GB that I can't run in 128GB that are interesting, where things really shift is at 1TB of memory which allows you run >1T parameter models w/ 4 bit quants reliably. 512GB is just on the edge of "enough", which is maybe the point of maximum frustration considering current memory prices.

    Personally, I can't justify dropping the dosh for a 512GB M5 Ultra, but I would be able to justify it to myself if I could get 1TB of memory, because it'd guarantee the flexibility with local models I currently am missing. Seems a huge miss to not offer this... for a price.

    • kamranjon 1 hour ago
      1tb would likely be ~$20k - given the current >$10k price tag of 256gb. Would you still be considering it at that price?
      • jdcasale 57 minutes ago
        I'd consider a 1tb machine at 20k, but I'm not going to pick up a 256gb one at all. 1TB fits a frontier-ish model in memory without massive quantization, which is a very interesting capability for a non-rack piece of compute.
        • epolanski 3 minutes ago
          But why...?

          At that point just rent proper GPUs in the cloud, you'd have way more power and pay only what you use for.

      • petercooper 57 minutes ago
        More likely double that, even. I think you'd still see many buyers there. You can spend like $16k alone on a RTX 6000 PRO with a mere 96GB of VRAM now..
      • tristor 54 minutes ago
        I would probably spend up to $30k if I could get 1TB of Unified Memory, because it would allow me a guarantee to run pretty much any local model I want, including >1T parameter models with reasonable quants. I wouldn't be surprised if 512GB is close to $20k when it becomes orderable in October. The justification is less about absolute price and more about price to what it enables. 512GB really doesn't enable much over 128GB for me, but 1TB would massively change things.

        I have a bit of paranoia/anxiety about AI, but it's not what most people are concerned with. I understand the limits of these tools very well, and still find them extremely useful. What concerns me is that it's going to become difficult to impossible in the future to run local models which have near-SOTA capabilities in a way in which you can exercise full control of the model. I see the writing on the wall, and its more than worth it for me to invest early to ensure my own capabilities. I am very much not a fan of our "you'll own nothing and be happy" directionality for the world, and I am (at least currently) privileged to have the means to slow that decline for my own self.

    • f0cus10 59 minutes ago
      chaining an option?
      • tristor 48 minutes ago
        RDMA is buggy and Thunderbolt only delivers 1/10th the throughput of native connectivity. 1TB of Unified Memory w/ 1.2TB/s of bandwidth with marginally ~$30k cost is a different story than 1TB of sorta Unified Memory w/ an effective 120GB/s of bandwidth with a marginally ~$40k cost + all the RDMA bugs.
        • Lwerewolf 26 minutes ago
          You need latency for token parallelism, not bandwidth. Hence actual RDMA that bypasses the software TCP stack (ROCe or whatever).
  • mannanj 4 minutes ago
    Am I the only one that now finds press releases like this similar to "AI Slop"

    I know there's tons of marketing language, buzz words and attempts at convincing me of some agenda that isn't super clear without lots of effort in "validating" the slop. I guess its not bad "slop" though if a human put in effort in editing it (imo >50% human curating = not really bad ai slop)

    Though I still would prefer I could just get the prompt. What human thoughts, direction and "prompt" went into writing this article? in the same way as we ask for the prompt for AI generated outputs, I would prefer it for human generated output too. For writing at the least. I could have saved time, got the purity of the argument, and got more clear information. I wonder if we can get a future where humans just express their intent with each other and stop trying to hide our agenda; I want a world we can trust each other greater and interpret and act on our goals without the noise of trying to impress or market to each other & the additional words that go into that.

  • Devasta 41 minutes ago
    If I were to get one of these, realistically what is the most advanced AI model I could run locally?
    • Zylokloto 17 minutes ago
      GLM 5.3 in ~q4 quantiziation with 4bits
  • bodash 22 minutes ago
    "512GB memory option for M5 Ultra coming late October"
  • speedping 16 minutes ago
    The article's headline contains an em dash. I wonder if it's AI-generated
    • Y-bar 13 minutes ago
      My sarcasm detector just made a small cloud of smoke. What does that mean, a buffer over or underflow??
    • post_break 14 minutes ago
      To me it seems like a cheeky way to preface the AI part of the title.