←back to thread

172 points marban | 2 comments | | HN request time: 0.001s | source
Show context
InTheArena ◴[] No.40051885[source]
While everyone has focused on Apple's power-efficiency on the M series chips, one thing that has been very interesting is how powerful the unified memory model (by having the memory on-package with CPU) with large bandwidth to the memory actually is. Hence a lot of people in the local LLMA community are really going after high-memory Macs.

It's great to see NPUs here with the new Ryzen cores - but I wonder how effective they will be with off-die memory versus the Apple approach.

That said, it's nothing but great to see these capabilities in something other then a expensive NVIDIA card. Local NPUs may really help with edge deploying more conferencing capabilities.

Edited - sorry, ,meant on-package.

replies(8): >>40051950 #>>40052032 #>>40052167 #>>40052857 #>>40053126 #>>40054064 #>>40054570 #>>40054743 #
chaostheory ◴[] No.40052032[source]
What Apple has is theoretically great on paper, but it fails to live up to expectations. Whats the point of having the RAM for running an LLM locally when the performance is abysmal compared to running it on even a consumer Nvidia GPU. It’s a missed opportunity that I hope either the M4 or M5 addresses
replies(8): >>40052327 #>>40052344 #>>40052929 #>>40053695 #>>40053835 #>>40054577 #>>40054855 #>>40056153 #
1. john_alan ◴[] No.40054855[source]
what are you talking about, it's literally the fastest single core retail CPU globally, and multicore is close too - https://browser.geekbench.com/processor-benchmarks
replies(1): >>40063026 #
2. edward28 ◴[] No.40063026[source]
I would take those benchmarks with a grain of salt, given that it shows a 96 core epyc loosing in multi thread to a 64 core epyc and a 32 core xeon.