Heavily upgraded M3 Ultra Mac Studio is great for AI projects

2»

Comments

  • Reply 21 of 38
    blastdoor said:
    At about 5 minutes and 30 seconds he says that building this with consumer PC hardware would be "quite expensive." I was looking for a fair bit more precision than that. 

    You seem to enjoy moving goal posts. 
    williamlondonblastdoor
     1Like 1Dislike 0Informatives
  • Reply 22 of 38
    Marvinmarvin Posts: 15,551moderator
    brianus said:
    I’m sure this was meant to be snarky, but for me it’s a genuine question: what are the envisioned real world use cases? What might a business (even a home one) use a local LLM for?

    The article mentions a hospital in the context of patient privacy, but what would that model actually be *doing*?
    In hospitals, AI models are reviewing patient scans to detect cancer:

    https://www.youtube.com/watch?v=Mur70YjInmI

    This is image analysis rather than text but text models can be used for medicine. There's an online AI for free here:

    https://duckduckgo.com/chat

    It can be asked about medical issues like if there's a pain somewhere, what could it be and what treatments are available e.g 'What medicine is typically used to treat acid reflux?'.

    In a clinical setting, a doctor would review the recommendations.

    In business, they'd be better off using a custom AI model that is trained on high quality data. A legal company might train a model on past cases and they can quickly find similar cases to use as references.

    Local models are usually more responsive (if the hardware is fast enough), don't get timeouts and you can save past prompts more easily. They would likely still be cloud-based so that all employees can access them from lightweight clients, just a company cloud server.
    blastdoor said:

    At about 5 minutes and 30 seconds he says that building this with consumer PC hardware would be "quite expensive." I was looking for a fair bit more precision than that. 
    Specs are listed here:

    https://geekbacon.com/2025/02/20/running-deepseek-r1-671b-locally-a-comprehensive-look/

    It needs multiple 3090 or higher GPUs + 512GB RAM. There's a video here showing a $2000 setup but it only runs at 3 tokens/s:

    https://www.youtube.com/watch?v=Tq_cmN4j2yY&t=2822s

    Another uses an Nvidia 6000 that costs around $7k for the GPU:

    https://www.youtube.com/watch?v=e-EG3B5Uj78&t=560s
    https://www.newegg.com/pny-vcnrtx6000ada-pb/p/N82E16814133886

    Performance is 4 tokens/s. The video in the article mentioned the M3 Ultra was around 17 tokens/s.

    This is one area where Nvidia and AMD are worse value and they do it on purpose because they make a lot of their revenue from this where they lower the memory in the consumer GPUs and charge a lot for enterprise GPUs with more memory that is needed for AI.

    This video tests Nvidia H100 GPUs x8 ($28k each - https://www.newegg.com/p/N82E16888892002 ), which gets 25 tokens/s:

    https://www.youtube.com/watch?v=bOp9ggH4ztE&t=433s

    If Nvidia sold a model of the H100 with 512GB of memory, it could probably compete with M3 Ultra but would cost more than $30k just for the GPU.

    Applications that need lots of unified memory is where Apple's hardware design is very competitive and they knew this when designing it.
    edited March 18
    baconstangblastdoorrezwitsrundhvidwatto_cobra
     3Likes 0Dislikes 2Informatives
  • Reply 23 of 38
    9secondkox29secondkox2 Posts: 3,342member
    Terrible value proposition. 

    I’ve a theory that Apple could sell this for much less and end up making more due to volume. Right now it’s very niche. 

    Would be great to see apple get the accolades it deserves as not only a performance per watt leader, but as an all-out straight up performance king. 

    It’s too bad they went with m3 ultra instead of 4. Would have been perfect timing to hurt Nvidias feelings. 
    rezwitsdanoxwatto_cobra
     1Like 2Dislikes 0Informatives
  • Reply 24 of 38
    blastdoorblastdoor Posts: 3,751member
    Marvin said:
    In hospitals, AI models are reviewing patient scans to detect cancer:

    https://www.youtube.com/watch?v=Mur70YjInmI

    This is image analysis rather than text but text models can be used for medicine. There's an online AI for free here:

    https://duckduckgo.com/chat

    It can be asked about medical issues like if there's a pain somewhere, what could it be and what treatments are available e.g 'What medicine is typically used to treat acid reflux?'.

    In a clinical setting, a doctor would review the recommendations.

    In business, they'd be better off using a custom AI model that is trained on high quality data. A legal company might train a model on past cases and they can quickly find similar cases to use as references.

    Local models are usually more responsive (if the hardware is fast enough), don't get timeouts and you can save past prompts more easily. They would likely still be cloud-based so that all employees can access them from lightweight clients, just a company cloud server.
    Specs are listed here:

    https://geekbacon.com/2025/02/20/running-deepseek-r1-671b-locally-a-comprehensive-look/

    It needs multiple 3090 or higher GPUs + 512GB RAM. There's a video here showing a $2000 setup but it only runs at 3 tokens/s:

    https://www.youtube.com/watch?v=Tq_cmN4j2yY&t=2822s

    Another uses an Nvidia 6000 that costs around $7k for the GPU:

    https://www.youtube.com/watch?v=e-EG3B5Uj78&t=560s
    https://www.newegg.com/pny-vcnrtx6000ada-pb/p/N82E16814133886

    Performance is 4 tokens/s. The video in the article mentioned the M3 Ultra was around 17 tokens/s.

    This is one area where Nvidia and AMD are worse value and they do it on purpose because they make a lot of their revenue from this where they lower the memory in the consumer GPUs and charge a lot for enterprise GPUs with more memory that is needed for AI.

    This video tests Nvidia H100 GPUs x8 ($28k each - https://www.newegg.com/p/N82E16888892002 ), which gets 25 tokens/s:

    https://www.youtube.com/watch?v=bOp9ggH4ztE&t=433s

    If Nvidia sold a model of the H100 with 512GB of memory, it could probably compete with M3 Ultra but would cost more than $30k just for the GPU.

    Applications that need lots of unified memory is where Apple's hardware design is very competitive and they knew this when designing it.
    Thanks! This is the kind of info I was looking for.
    muthuk_vanalingamwatto_cobra
     2Likes 0Dislikes 0Informatives
  • Reply 25 of 38
    Why on earth would I want to run an AI model?  Locally or otherwise?
    If you don't already know, perhaps you should pause on commenting in public until you've spent 15 seconds figuring it out.

    Suffice it to say that many people have very good reasons to do this.
    blastdoorneoncattiredskillswilliamlondonwatto_cobra
     3Likes 2Dislikes 0Informatives
  • Reply 26 of 38
    CheeseFreezecheesefreeze Posts: 1,395member
    As an AI-developer myself, a M3 Ultra would be an incredibly stupid purchase. The machine would only be good for a very limited set of AI-models.

    You'd be better off purchasing Digits for $3K, yes with 25% of the memory (128gb), and offload work to the cloud when needed,
    or chain two these machines for $6K. https://www.wired.com/story/nvidia-personal-supercomputer-ces/
    It would perform much better. Not only memory should be taken into account, but also the entire ecosystem around AI development 
    and performance across as well as internal storage and the type of chip and how it performs across models other than LLMs.

    The M3 Ultra is a best for video, 3D and post-production.
    neoncatwilliamlondonwatto_cobra
     1Like 2Dislikes 0Informatives
  • Reply 27 of 38
    blastdoorblastdoor Posts: 3,751member
    As an AI-developer myself, a M3 Ultra would be an incredibly stupid purchase. The machine would only be good for a very limited set of AI-models.

    You'd be better off purchasing Digits for $3K, yes with 25% of the memory (128gb), and offload work to the cloud when needed,
    or chain two these machines for $6K. https://www.wired.com/story/nvidia-personal-supercomputer-ces/
    It would perform much better. Not only memory should be taken into account, but also the entire ecosystem around AI development 
    and performance across as well as internal storage and the type of chip and how it performs across models other than LLMs.

    The M3 Ultra is a best for video, 3D and post-production.
    It sounds like Nvidia will have more powerful versions of that general concept, too.


    It strikes me that the big weakness with the Apple silicon machines is that the GPU just isn’t beefy enough. Apple might be better able to address that if they have the GPU on a separate die, which sounds like the plan with M5 pro and higher.
     0Likes 0Dislikes 0Informatives
  • Reply 28 of 38
    blastdoorblastdoor Posts: 3,751member
    As an AI-developer myself, a M3 Ultra would be an incredibly stupid purchase. The machine would only be good for a very limited set of AI-models.

    You'd be better off purchasing Digits for $3K, yes with 25% of the memory (128gb), and offload work to the cloud when needed,
    or chain two these machines for $6K. https://www.wired.com/story/nvidia-personal-supercomputer-ces/
    It would perform much better. Not only memory should be taken into account, but also the entire ecosystem around AI development 
    and performance across as well as internal storage and the type of chip and how it performs across models other than LLMs.

    The M3 Ultra is a best for video, 3D and post-production.
    In my case, I’m not an “AI developer” but I want to do local inference for privacy/security reasons. But that’s not my only use for a computer. I benefit a lot from Apple’s powerful CPU cores so I wouldn’t want to give that up. So I like the idea of using a Studio to meet both needs, even if the Apple GPU is a little weak compared to Nvidia.

    sadly for me, I can’t afford it now. DOGE has cut my income in half.
    watto_cobra
     1Like 0Dislikes 0Informatives
  • Reply 29 of 38
    If you go to ChatGPT and ask "Do people have different computing needs?" You will have successfully used an LLM to answer your own questions.
    So the principal reason that you can give for running an AI model is to ask it why I should run an AI model?  

    Not useful.  As expected.
    blastdoorwilliamlondonwatto_cobra
     1Like 2Dislikes 0Informatives
  • Reply 30 of 38
    If you don't already know, perhaps you should pause on commenting in public until you've spent 15 seconds figuring it out.

    Suffice it to say that many people have very good reasons to do this.
    Such as?

    I am obviously not one of those people, so am asking why.  Your answer is not illuminating.
    williamlondonwatto_cobra
     1Like 1Dislike 0Informatives
  • Reply 31 of 38
    bulk001bulk001 Posts: 822member
    If you need a computer for AI then buy the new Nvidia Blackwell spec’ed computers. Seems they will start at around 3k.
    williamlondon
     0Likes 1Dislike 0Informatives
  • Reply 32 of 38
    blastdoorblastdoor Posts: 3,751member
    Such as?

    I am obviously not one of those people, so am asking why.  Your answer is not illuminating.
    Are you retired? If so then don’t worry about it. 
     0Likes 0Dislikes 0Informatives
  • Reply 33 of 38
    brianus said:
    I’m sure this was meant to be snarky, but for me it’s a genuine question: what are the envisioned real world use cases? What might a business (even a home one) use a local LLM for?

    The article mentions a hospital in the context of patient privacy, but what would that model actually be *doing*?
    I think the big thing is for creative tasks. There are a lot of uses for AI in creative industries, but we don't want our material input being used to output somewhere else. So all image generation stuff is helpful to do locally. You know, as an artist, your content isn't being fed into the online system for others to use, but you still gain the value of using AI tools. Another amazing use case is text-to-video generation. It is prohibitively expensive to use text-to-video generation online, and very little output for the price. The ability to do that locally would be game-changing from a business perspective. Well worth the money. Leading-edge text-to-video models cost 1k or more to have enough output to make them valuable for business. Also there are tons of other use cases. 
    watto_cobra
     1Like 0Dislikes 0Informatives
  • Reply 34 of 38
    blastdoor said:
    Are you retired? If so then don’t worry about it. 
    I am not.  I work in enterprise software development.  I have seen nothing significantly useful from this AI revolution so far, just a lot of fakery, deception and disruption of trust.  These are unequivocally bad things to my mind.

    So I ask again, why would I want to run an AI model?  Locally or otherwise?
    williamlondonwatto_cobra
     1Like 1Dislike 0Informatives
  • Reply 35 of 38
    blastdoorblastdoor Posts: 3,751member
    I am not.  I work in enterprise software development.  I have seen nothing significantly useful from this AI revolution so far, just a lot of fakery, deception and disruption of trust.  These are unequivocally bad things to my mind.

    So I ask again, why would I want to run an AI model?  Locally or otherwise?
    It's probably best that you don't use them -- leave it to others. Just stick to your comfort zone. 
    tiredskillswatto_cobra
     1Like 1Dislike 0Informatives
  • Reply 36 of 38
    blastdoor said:
    It's probably best that you don't use them -- leave it to others. Just stick to your comfort zone. 
    If you can’t think of any answers it’s perfectly fine to just say so.
    watto_cobra
     1Like 0Dislikes 0Informatives
  • Reply 37 of 38
    blastdoorblastdoor Posts: 3,751member
    If you can’t think of any answers it’s perfectly fine to just say so.
    I'm not providing free tutoring, sorry. 
    tiredskillswatto_cobra
     1Like 1Dislike 0Informatives
  • Reply 38 of 38
    danoxdanox Posts: 3,665member
    Terrible value proposition. 

    I’ve a theory that Apple could sell this for much less and end up making more due to volume. Right now it’s very niche. 

    Would be great to see apple get the accolades it deserves as not only a performance per watt leader, but as an all-out straight up performance king. 

    It’s too bad they went with m3 ultra instead of 4. Would have been perfect timing to hurt Nvidias feelings. 



    Take a look at this link, the ultra M3 Mac Studio debuted at number 12 on the blender benchmark test 40 positions higher than the ultra M2 Mac Studio released one generation ago. Nvidia feelings will be hurt soon enough, and because they are a tech company they can see that convergence is probably only one generation away even the geeks on the tech sites are riled up because they can also see Apple’s trajectory. (Which is probably within a year)

    What does that mean? It means that Apple’s hardware/software future is very bright. (The ultra M5 or M6 will be at the top of the chart within one or two generations?).

    What this chart can’t show is the fact that the energy efficiency of the Apple Silicon chips are second to none at this time, most of the chips (Nvidia) featured on this list require 1000 watts or more, the Apple Silicon chips require less than 140 watts for everything CPU/SOC and GPU…. Users/Investors should look ahead. Apple is executing behind the scenes probably too much for the EU however who thinks Apple should share everything with their competition for the sake of fairness.

    https://opendata.blender.org/benchmarks/query/?compute_type=OPTIX&compute_type=CUDA&compute_type=HIP&compute_type=METAL&compute_type=ONEAPI&group_by=device_name&blender_version=4.3.0


    blastdoorneoncatwatto_cobra
     2Likes 1Dislike 0Informatives
Sign In or Register to comment.