Apple M3 Ultra • Hacker News Board

Re: Apple M3 Ultra

#201

Post by jihadjihad » Wed, Mar 05, 2025, 3:21 PM UTC

petecooper wrote: post #173

e40 wrote: post #139

Earlier quoted context omitted.

I torrent things from two different hosts on my gigabit network. The macos stack literally cannot handle the full bandwidth I have. It fails and the machine needs to be rebooted to fix it. It’s not pretty on the way into this state, either. Other remote connections to the computer are unreliable. On Linux, running the same app in a docker container works perfectly. Transmission is the app.

>Transmission is the app. Former Transmission user here. I realise you didn't ask, but you might find some improvements in qBittorrent.

I haven't had any issue running BiglyBT on my M1 MacBook, granted I don't run it all day every day but everything runs plenty fast for my needs (25-30 MB/s for well-seeded torrents).

Re: Apple M3 Ultra

#202

Post by api » Wed, Mar 05, 2025, 3:22 PM UTC

Half a terabyte could run 8 bit quantized versions of some of those full size llama and deepseek models. Looking forward to seeing some benchmarks on that.

Re: Apple M3 Ultra

#203

Post by exabrial » Wed, Mar 05, 2025, 3:22 PM UTC

InTheArena wrote: post #29

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.…

If Apple supported Linux (headless) natively, and we could rack m4 pros, I absolutely would use them in our Colo.

The CPUs have zero competition in terms of speed, memory bandwidth. Still blown away no other company has been able to produce Arm server chips that can compete.

Re: Apple M3 Ultra

#204

Post by dylan604 » Wed, Mar 05, 2025, 3:22 PM UTC

re-thc wrote: post #166

dylan604 wrote: post #117

Earlier quoted context omitted.

That’s what’s weird to me too. It’s not like they would lose sales of macOS as it is given away with the hardware. So if someone wants to buy Apple hardware to run Linux, it does not have a negative affect to AAPL

> So if someone wants to buy Apple hardware to run Linux, it does not have a negative affect to AAPL It does. Support costs. How do you prove it's a hardware failure or software? What should they do? Say it "unofficially" supports Linux? People would still try to get support. Eventually they'd have to test it themselves etc.

Apple has already been in this spot. With the TrashCan MacPro, there was an issue with DaVinci Resolve under OS X at the time where the GPU was cause render issues. If you then rebooted into Windows with BootCamp using the exact same hardware and open up the exact same Resolve project with the exact same footage, the render errors disappeared. Apple blamed Resolve. DaVinci blamed GPU drivers. GPU blamed Apple.

Re: Apple M3 Ultra

#205

Post by ryao » Wed, Mar 05, 2025, 3:23 PM UTC

bigyabai wrote: post #123

vlovich123 wrote: post #81

Earlier quoted context omitted.

This is for AI which is going to benefit more from use of metal / NPU than SIMD.

Sure, but larger models that fit in that 512gb memory are going to take a long time to tokenize/detokenize without hardware-accelerated BLAS.

Tokenization/detokenization does not use BLAS.

Re: Apple M3 Ultra

#206

Post by agloe_dreams » Wed, Mar 05, 2025, 3:23 PM UTC

lauritz wrote: post #46

They update the Studio to M3 Ultra now, so M4 Ultra can presumably go directly into the Mac Pro at WWDC? Interesting timing. Maybe they'll change the form factor of the Mac Pro, too? Additionally, I would assume this is a very low-volume product, so it being on N3B isn't a dealbreaker. At the same time, these chips must be very expensive to make, so tying them with luxury-priced RAM makes some kind of sense.

My understanding was that Apple wanted to figure out how to build systems with multi-SOCs to replace the Ultra chips. The way it is currently done means that the Max chips need to be designed around the interconnect. Theoretically speaking, a multi-SOC setup could also scale beyond two chips and into a wider set of products.

Re: Apple M3 Ultra

#207

Post by ntqvm » Wed, Mar 05, 2025, 3:23 PM UTC

Disappointing announcement. M4 brings a significant uplift over M3, and the ST performance of the M3 Ultra will be significantly worse than the M4 Max.

Even for its intended AI audience, the ISA additions in M4 brought significant uplift.

Are they waiting to put M4 Ultra into the Mac Pro?

Re: Apple M3 Ultra

#208

Post by BoredPositron » Wed, Mar 05, 2025, 3:23 PM UTC

AlchemistCamp wrote: post #197

InTheArena wrote: post #29

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.…

Keep in mind the minimum configuration that has 512GB of unified RAM is $9,499.

Still cheap if the only thing you look for is vram.

Re: Apple M3 Ultra

#209

Post by mschuster91 » Wed, Mar 05, 2025, 3:24 PM UTC

kstrauser wrote: post #183

InTheArena wrote: post #92

Earlier quoted context omitted.

No native docker support, no headless management options (enterprise strength), Limited QoS management, lack of robust python support (out of the box), interactive user focused security model.

1. I run Docker and Podman on my Macs. 2. If you mean MDM, there are several good options. Screen sharing and SSH are build in. 3. In what sense? 4. `uv python install whatever` is infinitely better than upgrading on the OS vendor’s schedule. 5. What does that affect?

> 1. I run Docker and Podman on my Macs.

That's using a Linux VM. The idea people are asking about is native process isolation. Yes you'd have to rebuild Docker containers based on some sort of (small) macOS base layer and Homebrew/Macports, but hey. Being able to even run nodejs or php with its thousands of files natively would be a gamechanger in performance.

Re: Apple M3 Ultra

#210

Post by dagmx » Wed, Mar 05, 2025, 3:24 PM UTC

bigyabai wrote: post #176

dagmx wrote: post #163

Earlier quoted context omitted.

You're comparing two different things. The compute level you’re talking about on the M3 Ultra is the neural engine. Not including the GPU. I expect the GPU here will be behind a 5090 for compute but not by the unrelated numbers you’re quoting. After all, the 5090 alone is multiple times the wattage of this SoC.

> After all, the 5090 alone is multiple times the wattage of this SoC. FWIW, normalizing the wattages (or even underclocking the GPU) will still give you an Nvidia advantage most days. Apple's GPU designs are closer to AMD's designs than Nvidia's, which means they omit a lot of AI accelerators to focus on a less-LLM-relevent raster performance figure. Yes, the GPU is faster than the NPU. But Apple's GPU designs haven…

M2 Ultra is ~250W (averaging various reports since Apple don’t publish) for the entire SoC.

5090 is 575W without the CPU.

You’d have to cut the Nvidia to a quarter and then find a comparable CPU to normalize the wattage for an actual comparison.

I agree that Apple GPUs aren’t putting the dedicated GPU companies in danger on the benchmarks, but they’re also not really targeting it? They’re in completely different zones on too many fronts to really compare.