651–660 of 1001 posts
Earlier quoted context omitted.
You’re largely correct for training models Where this hardware shines is inference (aka developing products on top of the models themselves)
True. But with Project Digits supposedly around the corner, which supposedly costs $3,000 and supports ConnectX and runs Blackwell; what's the over-under on just buying two of those at about half the price of one maxed M3 Ultra Mac Studio?
Earlier quoted context omitted.
I don't think there's a huge use-case locally, if you're happy with the subscription cost and privacy. That is, yet. Give it maybe 2 years and someone will probably invent something which local inference would seriously benefit from. I'm anticipating inference for the home appliances (something mac mini form factor that plugs into your router) but that's based on what would make logical sense for consumers, not what…
Thanks. >> Apple seems to be using LPDDR, but HBM will also likely be a key tech. SK Hynix and Samsung are the most reputable for both. So not much Micron? Any US based stocks to invest in? :-)
Earlier quoted context omitted.
It's still boiling down to hardware and software differences. In terms of hardware - Apple designs their GPUs for GPU workloads, whereas Nvidia has a decades-old lead on optimizing for general-purpose compute. They've gotten really good at pipelining and keeping their raster performance competitive while also accelerating AI and ML. Meanwhile, Apple is directing most of their performance to just the raster stuff. The…
> keeping their raster performance competitive while also accelerating AI and ML. Meanwhile, Apple is directing most of their performance to just the raster stuff. They could pivot to an Nvidia-style design, but that would be pretty unprecedented (even if a seemingly correct decision). Isn't Apple also focusing on the AI stuff? How has it not already made that decision? What would prevent Apple from making that decis…
Yes, but not with their GPU architecture. Apple's big bet was on low-power NPU hardware, assuming the compute cost of inference would go down as the field progressed. This was the wrong bet - LLMs and other AIs have scaled up better than they scaled down.
> How has it not already made that decision? What would prevent Apple from making that decision?
I mean, for one, Apple is famously stubborn. They're the last ones to admit they're wrong whenever they make a mistake, presumably admitting that the NPU is wasted silicon would be a mea-culpa for their AI stance. It's also easier to wait for a new generation of Apple Silicon to overhaul the architecture, rather than driving a generational split as soon as the problem is identified.
As for what's preventing them, I don't think there's anything insurmountable. But logically it might not make sense to adopt Nvidia's strategy even if it's better. Apple can't neccessarily block Nvidia from buying the same nodes they get from TSMC, so they'd have to out-design Nvidia if they wanted to compete on their merits. Even then, since Apple doesn't support OpenCL it's not guaranteed that they would replace CUDA. It would just be another proprietary runtime for vendors to choose from.
> Can you give an example of where Metal wants you to write something yourself whereas CUDA is pre-rolled?
Not exhaustively, no. Some of them are performance-optimized kernels like cuSPARSE, some others are primative sets like cuDNN, others yet are graph and signal processing libraries with built-out support for industrial applications.
To Apple's credit, they've definitely started hardware-accelerating the important stuff like FFT and ray tracing. But Nvidia still has a decade of lead time that Apple spent shopping around with AMD for other solutions. The head-start CUDA has is so great that I don't think Apple can seriously respond unless the executives light a fire under their ass to make some changes. It will be an "immovable rock versus an unstoppable force" decision for Apple's board of directors.
Earlier quoted context omitted.
between 4.25 to 3.5 TPS (tokens per second) on the Q4 671b full model. 3.5 - 4.25 tokens/s. You're torturing yourself. Especially with a reasoning model. This will run it at 40 tokens/s based on rough calculation. Q4 quant. 37b active parameters. 5x higher price for 10x higher performance.
Also you don't have to deal with Windows. Which people who do not understand Apple are very skilled at not noticing. If you've ever used git, svn, or an IDE side by side on corporate Windows versus Apple I don't know why you would ever go back.
The custom build would work great though, and even moreso in a server room and as well continues to reveal by comparison how excessively Apple prices it's components.
Whoa. M3 instead of M4. I wonder if this was basically binning, but I thought that I had read somewhere that the interposer that enabled this for the M1 chips where not available. That Said, 512GB of unified ram with access to the NPU is absolutely a game changer. My guess is that Apple developed this chip for their internal AI efforts, and are now at the point where they are releasing it publicly for others to use.…
M1 Max - 24 to 32 GPU cores
M2 Max - 30 to 38 GPU cores
M3 Max - 30 to 40 GPU cores
M4 Max - 32 to 40 GPU cores
I also looked up the announcement dates for the Max and the Ultra variant in each generation.
M1 Max - October 18, 2021
M1 Ultra - March 8, 2022
M2 Max - January 17, 2023
M2 Ultra - June 5, 2023
M3 Max - October 30, 2023
M3 Ultra - March 12, 2025
M4 Max - October 30, 2024
> My guess is that Apple developed this chip for their internal AI efforts
As good a guess as any, given the additional delay between the M3 Max and Ultra being made available to the public.
Earlier quoted context omitted.
They use their own M chips for IA. They are far more advanced on AI than the majority of company. They are using OpenAI for now but in couple months they will own the full chain of value.
we’ve heard that claim for the past three years, but every effort by them points to the opposite. don’t get me wrong, I would love for Apple Intelligence to be smart enough on my iPhone and on my Mac, but honestly, the current version is a complete disappointment.
1. Small models running locally with well-established tool interfaces (“app intents”)
2. Large models running in a bespoke cloud that can securely and quickly load all relevant tokens from a device before running inference
No AI lab is even close to what Apple is trying to deliver in the next ~12 months
Earlier quoted context omitted.
What people who did not actually work with this stuff in practice don't realize is the above statement only holds for batch size 1, sequence size 1. For processing the prompt you will need to read all the weights (which isn't a problem, because prefill is compute-bound, which, in turn is a problem on a weak machine like this Mac or an "EPYC build" someone else mentioned). Even for inference, batch size greater than 1…
No one who is using this for home use cares about anything except batch size 1 sequence size 1.
Earlier quoted context omitted.
I've been buying and using MBP for 6 or 7 years now, and just assumed I could run Linux on one if I wanted to. I just spent a couple of days trying to get a 2018 MBP working with Linux and found out [edit to clarify] that my other ARM MBP basically won't work. I just want a break from MacOS, I'll be buying a Thinkpad and will probably never come back. This isn't my moaning, I understand it's their market, but if thei…
Loved my M1 mini, loved my M2 air. I've moved on to 2024 HP Elitebook with an AMD R7 8840U, 1TB replaceable NVME, 32gb of socketed DDR5. 14in laptop with a serviceable enough 1920x1200 matte screen. $800 and a 3 hour drive to the nearest Microcenter. I gave Apple another try (refused apple from 2009-2020 because of the nvidia era issues) and I just can't stomach living off of piles of external drives anymore to make…
Earlier quoted context omitted.
They didn't increase the memory bandwidth. You can get the same memory bandwidth, which is available on the M2 Studio. Yes, yes, of course you can get 512 gigabytes of uRAM for 10 grand. The the question is if a llm will run with usable performance at that scale? The point is there's diminishing returns despite having enough uRAM with the same amount of memory bandwidth even with increased processing speed of the new…
Since no one specifically answered your question yet, yes, you should be able to get usable performance. A Q4_K_M GGUF of DeepSeek-R1 is 404GB. This is a 671B MoE that "only" has 37B activations per pass. You'd probably expect in the ballpark of 20-30 tok/s (depends on how much actually MBW can be utilized) for text generation. From my napkin math, the M3 Ultra TFLOPs is still relatively low (around 43 FP16 TFLOPs?),…
$9499
What ever happening to competition in computing?
Computing hardware competition used to be cut throat, drop dead, knife fight, last man standing brutally competitive. Now it's just a massive gold rush cash grab.