Apple M3
Central processing unitWikipedia
36
MENTIONS
10
EPISODES
10
PODCASTS
Search complete. 36 mentions across 10 episodes found for "Apple M3".
Sep 24, 2026
622: Just Me and My Sad Friends
F
39:45Federico ViticciHOST
Okay.
F
39:48Federico ViticciHOST
Coming from the M3 Ultra Mac Studio, which I still have with 512 gigs of RAM, the main thing that this computer has allowed is... being able to use the best local models that fit on this machine with the kind of performance that makes them nice to use in apps.
F
40:16Federico ViticciHOST
Like these local models could be used before in terms of fitting on the computer, right? And even on the M3 Ultra, I could even fit bigger models because I have the 512 gig version.
F
40:31Federico ViticciHOST
But even if they technically fit in the machine, in memory and in storage, they were not necessarily nice to use because they were slow.
F
40:43Federico ViticciHOST
And they were slow in two different metrics.
12 MINS LATER
F
52:59Federico ViticciHOST
thing right now and I think if they're serious about this like when I when I when I mentioned like you gotta package it up in a way that makes sense they have a lot of work to do instead of just saying well just wait for you know the developer the open source community to figure it out But that's not a way to build a sustainable product over time.
F
53:24Federico ViticciHOST
So I think they should maybe take a look at what NVIDIA is doing with the Sparks and be a little more invested into reaching out to the community.
F
53:38Federico ViticciHOST
For example, when a new computer comes out, having a more prepared package to give out to people like me or other content creators that I saw on YouTube that have the same review unit and be like, here's this thing that you can test that we know is already optimized for the M5 Ultra and we know is going to give you the kind of performance that is way above the M3 Ultra.
Connected 622: Just Me and My Sad Friends
F
39:45Federico ViticciHOST
Okay.
F
39:48Federico ViticciHOST
Coming from the M3 Ultra Mac Studio, which I still have with 512 gigs of RAM, the main thing that this computer has allowed is... being able to use the best local models that fit on this machine with the kind of performance that makes them nice to use in apps.
F
40:16Federico ViticciHOST
Like these local models could be used before in terms of fitting on the computer, right? And even on the M3 Ultra, I could even fit bigger models because I have the 512 gig version.
F
40:31Federico ViticciHOST
But even if they technically fit in the machine, in memory and in storage, they were not necessarily nice to use because they were slow.
F
40:43Federico ViticciHOST
And they were slow in two different metrics.
12 MINS LATER
F
52:59Federico ViticciHOST
thing right now and I think if they're serious about this like when I when I when I mentioned like you gotta package it up in a way that makes sense they have a lot of work to do instead of just saying well just wait for you know the developer the open source community to figure it out But that's not a way to build a sustainable product over time.
F
53:24Federico ViticciHOST
So I think they should maybe take a look at what NVIDIA is doing with the Sparks and be a little more invested into reaching out to the community.
F
53:38Federico ViticciHOST
For example, when a new computer comes out, having a more prepared package to give out to people like me or other content creators that I saw on YouTube that have the same review unit and be like, here's this thing that you can test that we know is already optimized for the M5 Ultra and we know is going to give you the kind of performance that is way above the M3 Ultra.
Raspberry Pi Blocks RAM Upgrades
V
8:32Vin StoneHOST
Cool.
J
8:34Jill BryantHOST
And also the Mac Studio powered by the M3 Ultra is not yet supported.
J
8:40Jill BryantHOST
And so that'll probably be their next big task after they get the other M3 and M3 Pro and M3 Max support.
J
8:52Jill BryantHOST
But the Asahi Linux M3 update can easily be installed in the macOS terminal.
Googlebooks are coming for your Mac
D
2:05David ImelHOST
Next, our $12,300 M5 Ultra Max Studio review is out, and as expected, it absolutely tore through our benchmark tests.
D
2:14David ImelHOST
Our nearly maxed out M5 Ultra came out about 30% faster than our similarly specced M3 Ultra from last year in both single-core and multi-core synthetic CPU tests.
D
2:25David ImelHOST
On a heavier GPU rendering test Cinebench, the M5 Ultra scored 63% higher.
D
2:30David ImelHOST
And finally, the Wall Street Journal reported that Google's Gemini model broke containment in May and hacked three separate companies.
Local AI Gets Serious on the M5 Ultra Mac Studio
F
9:52Federico ViticciHOST
And you're looking at this new GPU with 80 cores, and inside each core, there's a neural accelerator with a new architecture.
F
9:59Federico ViticciHOST
So this is... something that apple started doing as we saw before in the earlier in the m5 generation putting a neural accelerator inside each gpu core so you got 80 of those uh in the in the m5 ultra in addition to the new gpu uh which you know on average apple says should perform like up to four times you know better in terms of compute than the m3 ultra and like nine times better or something than the m1 ultra So I think sort of the angle of my story was I've been using the Mac Studio as a local server for all kinds of things for the past year.
F
10:37Federico ViticciHOST
But especially this summer, I went all in with local AI on the Mac Studio because I had this big project, the iOS 27 review.
F
10:48Federico ViticciHOST
that I structured in such a way that required an agent to be running at all times, meaning every five minutes, an agent would actually fire up and do some processing.
F
11:00Federico ViticciHOST
Multiple of those agents with different schedules.
F
11:02Federico ViticciHOST
So effectively, it was always running something.
F
11:05Federico ViticciHOST
In that case, the M3 Ultra Max Studio was running DeepSeek V4 Flash.
F
11:10Federico ViticciHOST
And I structured it in a way that I had to be using a local model.
Episode 156: To Pro or not to Pro
L
41:20Luke MianiHOST
Oh, this was pretty crazy.
L
41:21Luke MianiHOST
The M5 Ultra absolutely smoking the M3 Ultra.
L
41:28Luke MianiHOST
Not surprisingly, given that the M5 Max was at 225,000 in the medal score, the M3 Ultra was at 230,000.
L
41:36Luke MianiHOST
So you're already 99% of the way there with the max chip.
L
41:42Luke MianiHOST
You put two of them together, yeah, 360K.
L
41:44Luke MianiHOST
That's an insane jump over the M3 Ultra.
L
41:50Luke MianiHOST
But where's the M6? Oh, yeah, the M6...
L
41:53Luke MianiHOST
Wow, so the M6 is scoring in between an M2 and an M4 Pro.
709: Steel-Cable Insurance
C
20:21Casey LissHOST
And then finally, the M5 Ultra, the CPU is roughly the same as the M5 Max for single core, which is to be expected, I think.
C
20:31Casey LissHOST
But multi-core, it's almost 40% better than the M3 Ultra.
C
20:36Casey LissHOST
So again, M3 to M5 is an almost 40% increase.
C
20:40Casey LissHOST
M5 Max to M5 Ultra, a 60% increase.
C
20:45Casey LissHOST
That is astonishing to me.
C
20:47Casey LissHOST
So again, M3 Ultra to M5 Ultra, uh, 40% increase, but M5 Max to M5 Ultra, 60, almost 60% increase.
J
20:56John SiracusaHOST
Yeah, I mean, you would, uh, it's t- it's tricky because like, hey, isn't it two M5 Maxes put together? Shouldn't it be 100% increase 'cause you double everything? And that's where you get into some of the-- obviously, there's overhead of the, you know, the, the way they do the interposer and blah, blah, blah.
J
21:08John SiracusaHOST
But also, are these benchmarks like, uh, what kind of data dependencies are in these benchmarks? Like, there's a whole bunch of things that limit the exploitable parallelism in CPU stuff.
Ep 83: Nick Hakim has your gear on long-term loan
W
59:53Will BettsHOST
You're living inside this house with the studio in an open space, lots of natural light, big windows, but it's still cozy and homely.
W
60:03Will BettsHOST
Your computer is a souped-up Mac Studio M3 Ultra with 96 gigabytes of RAM.
W
60:09Will BettsHOST
Your interface is an Apogee Symphony I/O Mark 2.
W
60:13Will BettsHOST
Your DAW is Ableton 12 Suite.
Could Anthony Volpe EARN a FUTURE role with the Yankees in his stint?
J
6:09Jake EllenbogenHOST
So I have like, um, like stands for like my laptop, but I don't use a laptop anymore.
J
6:18Jake EllenbogenHOST
As you know, I have this giant computer, this M3 Ultra.
J
6:22Jake EllenbogenHOST
And, um, I put other things on the stands.
J
6:26Jake EllenbogenHOST
So like, I'll literally put like, like things to remember.
16 MINS LATER
G
22:29Gary Sheffield Jr.HOST
Well, so do you, Jake.
G
22:30Gary Sheffield Jr.HOST
You just have bad Wi-Fi in your area.
G
22:32Gary Sheffield Jr.HOST
And then two, I'm in a basement on my computer with a MacBook Pro microphone.
G
22:41Gary Sheffield Jr.HOST
So, we're grinding.
The Manadalorian Audacity. EP# 2120
M
47:44Max SmartHOST
So not just the AI engine that used to be separate.
M
47:48Max SmartHOST
It's up to 4.5 times faster than with AI than, say, the M3 Ultra.
M
47:55Max SmartHOST
It's 40% faster graphics than the M3 Ultra.
M
48:00Max SmartHOST
It does include 32 core neural engine, and that's separate.
M
48:05Max SmartHOST
So you've got the neural accelerators in the GPU, and you still have those neural engines.
M
48:31Max SmartHOST
If you have $12,000, you can get the M5 Ultra Max Studio with 512 gig of unified memory combined.
M
48:42Max SmartHOST
By the way, that has 1.2 terabytes per second of memory bandwidth.
M
48:47Max SmartHOST
That's 50% more than the M3 Ultra.