Base models only: - M1 | 5 nm | 8 (4P+4E) | GPU 7–8 | 16-core Neural | Memory Bandwidth: 68.25 GB/s | Unified Memory: 16 GB | Geekbench6 ~2346 / 8346 - M2 | 5 nm (G2) | 8 (4P+4E) | GPU 8–10 | 16-core Neural | Memory Bandwidth: 100 GB/s | Unified Memory: 24 GB | Geekbench6 ~2586 / 9672 - M3 | 3 nm (first-gen) | 8 (4P+4E) | GPU 8–10 | 16-core Neural | Memory Bandwidth: 100 GB/s | Unified Memory: 24 GB | Geekbench6 ~296…
Did TSMC 2nm slip to next year, or was it always planned to be 2026?
Apple M5 chip
721–730 of 1001 posts
Re: Apple M5 chip
#722Too underwhelming. Apple under Tim Cook has been running out of steam. What prevents Apple from having 100s of GPU cores and higher memory bandwidth? They need to catch the AI wave before they perish under it.
What are you talking about? People love Macs for running local LLMs.
And it ruins battery life.
For coding it's on par with GPT3 at best which is amateur tier these days.
It's good for text to speech and speech to text but PCs can do that too.
Re: Apple M5 chip
#723Base models only: - M1 | 5 nm | 8 (4P+4E) | GPU 7–8 | 16-core Neural | Memory Bandwidth: 68.25 GB/s | Unified Memory: 16 GB | Geekbench6 ~2346 / 8346 - M2 | 5 nm (G2) | 8 (4P+4E) | GPU 8–10 | 16-core Neural | Memory Bandwidth: 100 GB/s | Unified Memory: 24 GB | Geekbench6 ~2586 / 9672 - M3 | 3 nm (first-gen) | 8 (4P+4E) | GPU 8–10 | 16-core Neural | Memory Bandwidth: 100 GB/s | Unified Memory: 24 GB | Geekbench6 ~296…
Let's see if I can turn this into an ASCII table and have it survive HN's reformatting. +------+------------------+--------------+----------+----------------+-------------------+-------------------+---------------------------+ | Chip | Process | CPU Cores | GPU | Neural Engine | Memory Bandwidth | Unified Memory | Geekbench6 (Single/Multi) | +------+------------------+--------------+----------+----------------+------…
Chip | Process | CPU | GPU | Neural | Memory | Unified | Geekbench6
| | Cores | | Engine | Bandwidth | Memory | Single / Multi
-----|---------|-----------|------|---------|-------------|---------|----------------------
M1 | 5 nm G1 | 8: 4P+4E | 7–8 | 16-core | 68.25 GB/s | 16 GB | 2346 / 8346
M2 | 5 nm G2 | 8: 4P+4E | 8–10 | 16-core | 100 GB/s | 24 GB | 2586 / 9672
M3 | 3 nm G1 | 8: 4P+4E | 8–10 | 16-core | 100 GB/s | 24 GB | 2965 / 11565
M4 | 3 nm G2 | 10: 4P+6E | 8–10 | 16-core | 120 GB/s | 32 GB | 3822 / 15031
M5 | 3 nm G3 | 10: 4P+6E | 10 | 16-core | 153 GB/s | ≤32 GB | 4133 / 15437 (9 core)Re: Apple M5 chip
#724Re: Apple M5 chip
#725Apple's software division has lost their way. They've done nothing but add flashy features and move buttons around, deprecating things and breaking backwards compatibility (yeah, 32bit has been awhile now, but alas), meanwhile retreating on stability. Snow Leopard still remains the company's crown achievement. 0 bloatware, 0 "mobile features on desktop" (wtf is this even a thing?), tuned for absolute speed and stabil…
I've heard about rounded corners and low information density windows in Tahoe, but what "mobile features on desktop" are in Sequoia and earlier? The App Store? Launchpad? iCloud? Notifications? You don't need to use those.
Re: Apple M5 chip
#726Re: Apple M5 chip
#727Re: Apple M5 chip
#728Earlier quoted context omitted.
> A lot of Apple hardware is impressive on paper, but I will never buy a Mac that can't run Linux. They run Linux actually very well, have you ever tried Parallels or VMware Fusion? Especially Parallels ships with good softwaer drivers for 2d/3d/video acceleration, suspend, and integration into the host OS. If that is not your thing, the new native container solution in Tahoe can run container from dockerhub and co.…
Last I looked... extensive telemetry and a sealed boot volume that makes it impractical to turn off even if theoretically possible. There are other problems of course.
Re: Apple M5 chip
#729When it allows installing any Linux with working drivers, I will consider it. Otherwise, you can go back to your garage and I will continue to make fun of people using Macs.
Re: Apple M5 chip
#730Earlier quoted context omitted.
Amazing. My M3Max is going to look like a paper-weight very soon. And that's fine by me. When I get an M6 or M7Max to replace it it'll be amazing.
I’m trying to find any reason I can that my M1 Max needs replacement; it’s hard. How do you justify it?