Hacker News Reader

Comment by UncleOxidant | Hacker News Reader

> If AMD keeps with tradition, which we fully expect, we will see these monstrous APU chips come to desktop PCs in the future.

How far in the future? I don't need another laptop, but would be nice to have a box to run local llms on. If these things can run LLMs at a decent clip then this would be sort of a "shut up and take my money" situation.

View on HN

I hope the LLM benchmarks announced were reasonable and not something gross like using a model that doesn't swap on the Strix Halo, but does on a 4090.

HP announced a HP Z2 mini g1a, which is bigger than a NUC, but I believe still considered a SFF:

https://www.pcworld.com/article/2567865/hp-z2-mini-g1a-packs...

It's gotta be swapping or something. The 4090 is faster (and far more expensive) than Strix Halo in every way.

After digging it looks like 70B Q4 requires 35GB or so. So yes the AMD comparison is a strix halo not swapping vs a 4090 that is swapping. Seems kinda misleading, but is a real advantage for larger models.

The problem with using these on a AM5 motherboard would be that these chips have quad channel ddr5, while AM5 has 2 memory channels.

HP already announced a mini workstation with this chip.

I'm seeing a laptop [1] do you have a link to the workstation?

EDIT: Oh, I see they're calling the laptop a workstation.

[1] https://liliputing.com/hp-zbook-ultra-14-g1a-mobile-workstat...

There's a laptop AND a desktop, called the HP Z2 Mini G1a.

https://www.pcworld.com/article/2567865/hp-z2-mini-g1a-packs...

"coming soon" and no pricing.

Sure, but the previous iterations (like Strix in the non-halo form) and similar AMD laptop chips are popular with numerous SFFs from the likes of ASUS, ASRock, Gigabyte, Beelink, Minisforum, GMKtex, Lenovo, and many others.

I've heard similar rumors of similar SFFs from framework, system76, and similar VARs.

The Strix Halo does seem pretty compelling for those that want less volume, power, and money than a discrete GPU. I'd love a small SFF with either 128GB ram (some parts will have the ram in the package)) or two CUDIMM slots.

Generally SFFs use laptop parts, but tend to be out a few months later than the equivalent laptops.

I expect similar with the Strix Halo/AI Max.

Reply on news.ycombinator.com