271–280 of 789 posts
Earlier quoted context omitted.
For inference, Apple chips are great due to a high memory bandwidth. Mac Studio is a popular choice in the local Llama community for this particular reason. It's a cost effective option if you need a lot of memory plus a high bandwidth. The downside is poor training performance and Metal being a less polished software stack compared to CUDA. I wonder if a little cluster of Mac Minis is a good option for running concu…
The memory bandwidth on Apple silicon is only sometimes comparable to, and in many cases worse than, that of a GPU. For example, an nVidia RTX 4060 Ti 16GB GPU (not a high-end card by any means) has memory bandwidth of 288GiB/sec, which is more than double that of the M4 CPU. On the higher end, building a machine with 6 to 8 24GB GPUs such as RTX 3090s would be comparable in cost (as well as available memory) to a hi…
https://www.apple.com/mac-studio/specs/
Edit: since my reply you have edited your comment to mention the Studio, but the fact remains that the M2 Max has at least ~40% greater bandwidth than the number you quoted as an example.
> Mac mini is Apple’s first carbon neutral Mac Hats off! I didn't expect the Mac to be next in line for the carbon neutral goals. But they did it!
Easy if you just buy meaningless carbon credits.
This looks to me like one instance where the incentives are decently working, at least to some point.
Earlier quoted context omitted.
This is huge for AI / ML at least for inference. Apple chips are among the most efficient out there for that sort of thing, the only downside is the lack of cuda
> Apple chips are among the most efficient out there for that sort of thing Not really? Apple is efficient because they ship moderately large GPUs manufactured on TSMC hardware. Their NPU hardware is more or less entirely ignored and their GPUs are using the same shader-based compute that Intel and AMD rely on. It's not efficient because Apple does anything different with their hardware like Nvidia does, it's efficie…
Love to see that it still starts at $599. My M2 Mac Mini that I got for $499 is my favorite gaming computer I've had in a long time. Runs many games like WoW, Dota, League of Legends, etc great. Anything that it doesn't run due to MacOS I use GeForce Now over ethernet. And this was with 8gb unified memory, now with 16gb it'll be even better value. Very excited to see how the GPU has improved in the M4, especially the…
Can you elaborate? Thinking of setting up a MacMini for my kids but worried about lack of gaming options for them (I haven't gamed on a Mac in a dozen years and the state of gaming on MacOS was sad back then).
Earlier quoted context omitted.
It's not just RAM. It's Unified RAM. So that memory is also used for the GPU & Neural Cores (which is for Apple Intelligence). This is actually why companies moved away from the unified memory arch decades ago. It'll be interesting to see as AI continues to advance, if Apple is forced to depart from their unified memory architecture due to growing GPU memory needs.
At this point it feels like (correct me if I'm am wrong) that Apple's AI is often performed "in the cloud". I suspect though that if Apple moves increasingly to on-device AI (as I suspect they will — if not for bandwidth and backend resource reasons then for privacy ones) Apple's Silicon will have adopted more and more specialized AI components — perhaps diminishing the need for use of off-board memory.
Earlier quoted context omitted.
> This seems small, but it would have been almost blasphemy under the jobs era. I feel like Jobs was a lot more pragmatic than we give him credit for. I mean we had the HP iPods, iTunes on Windows etc. And the iMac's catch copy was "BYODKM" at the very start, fully putting the spotlight on third parties and composability.
I've followed Apple all my life and never heard of HP iPods!
Earlier quoted context omitted.
No mention of the SSD size that was the reason I returned my Mac mini 256Gb last year was just a pain juggling files
You might be interested in this then - https://satechi.net/collections/ssd-enclosures Upgrade your memory and connect it externally over USB-C. It works brilliantly
Earlier quoted context omitted.
As discussed in the iMac thread yesterday, LPCAMM2 makes it possible. There are LPCAMM2 modules with the same 7500 MT/s spec as the M4s integrated memory, and two of them running in parallel would match the M4 Pro. https://www.anandtech.com/show/21390/micron-ships-crucialbra... Even if Apple wanted to support modular memory, which they obviously don't, the ultra-tiny form factor of the new Mini would probably still r…
No way the new Mini is too small to allow upgradability. You can buy a Windows mini PC that is not only smaller than the new Mini but also allows upgrading both RAM and SSD. And that's without using LPCAMM2 - just normal SO-DIMMs. (Example: https://trigkey.com/products/trigkey-green-g4-16g-500g-n100 )
It's basically a 12 year old PC shrunk into a tiny box and low power budget.
Earlier quoted context omitted.
Isn't steamdeck a better option for this use case?
I have a Steam Deck, Asus ROG Ally, M2 Mac Mini, M1 Pro laptop, M2 Max laptop (work). All of this runs on either an LG C3 42" OLED or a 34" 1440p ultrawide. Linux GeForce Now can only do 720p or 1080p, can't remember which. Also, it's just kind of laggy in desktop mode. The Macs run so much smoother. My current "main" desktop is actually my Asus ROG Ally. I use one USB C hub that is capable of 4k120hz, and I can move…
Perennial truth since XP