I’d argue not. It’s as modular/repairable as the platform can be (with them outright stating the problematic soldered RAM), and not exorbitantly priced for what it is.

But what I think is most “Framework” is shooting for a niche big OEMs have completely flubbed or enshittified. There’s a market (like me) that wants precisely this, not like a framework-branded gaming tower or whatever else a desktop would look like.

And the “base” of this is physically more like a cut down M4 Pro than a regular M4.

The AI max chips are a completely different platform, more than double the physical silicon size of most minipc chips.

Yeah.

But that’s AMD’s fault, as they gimped the GPU so much on the lower end. There should be a “cheap” 8-core, 1-CCD part with close to the full 40 CUs… But there is not.

Probably still is, lol.

Apple stuff works best in the Apple ecosystem, though most of what works on Windows can work on linux.

DRAM is so cheap and ubiquitous that they will probably keep using that, barring any massive breakthroughs. The “persistence after power-off” is nice to have, but not strictly needed.

There’s lots of workstation niches that are gated by VRAM size, like very complex rendering, scientific workloads, image/video processing… It’s not mega fast, but basically this can do things at a reasonable speed that you’d normally need a $20K+ computer to even try. Like, if something takes hours on an A6000 Ada or an A100, just waiting overnight on one of these is not a big deal. Cashing or failing to launch on a 4090 or 7900 XTX is.

That aside, the IGP is massively faster than any other integrated graphics you’ll find. It’s reasonably power efficient.

This has no X3D, the L3 is shared between CCDs. The only odd thing about this is it has a relatively small “last level” cache on the GPU/Memory die, but X3D CPUs are still kings of single-threaded performance since that L3 is right on the CPU.

This thing has over twice the RAM bandwidth of the desktop CPUs though, and some apps like that. Just depends on the use case.

The 5090 is basically useless for AI dev/testing because it only has 32GB. Mind as well get an array of 3090s.

The AI Max is slower and finicky, but it will run things you’d normally need an A100 the price of a car to run.

But that aside, there are tons of workstations apps gated by nothing but VRAM capacity that this will blow open.

You don’t have to pick and choose, you can dual boot.

But the only thing I boot Windows for these days is gaming and Microsoft Teams. Linux has come a long way since 2008.

It will be faster than most next-gen laptops, and it’s much cheaper than a similarly-specced Asus Z13. Strix Halo uses a quad channel 8533Mhz bus, 2 full Zen CCDs like you find in desktops/servers, and a 40 CU GPU. Its more than twice the size/performance of two true “laptop chips” put together.

Everything except the APU/RAM/Mobo combo is upgradable, and you don’t have to replace the whole machine if the board fails.

I mean, if you don’t need that kind of compute/RAM, this system is not for you, and old gaming desktops are probably better deals for pure gaming. But this thing has a niche.

deleted by creator

Or linux.

This thing makes a whole lot of pricey workstations obsolete.

Eventually most system RAM will have to be packaged anyway. Physics dictates that one pays a penalty going over pins and mobo traces, and it gets more severe with every advancement.

It’s possible that external RAM will eventually evolve into a “2nd tier” of system memory, for background processes, spillover, inactive programs/data, things like that.

As others said.

In this context it would be one of the CPU/Memory combinations framework offers: https://en.wikipedia.org/wiki/List_of_AMD_Ryzen_processors#Strix_Halo_(Zen_5/RDNA3.5/XDNA2_based)

Holy moly this is awesome! I am in for the 128GB SKU.

That’s 96GB of usable VRAM! And way more CPU bandwidth than any desktop Zen chip.

I know people are going to complain about non upgradable memory, but you can just replace the board, and in this case it’s so worth it for the speed/power efficiency. This isn’t artificial crippling, it physically has to be soldered, at least until LPCAMM catches on.

My only ask would be a full X16 (or at least a physical X16/electrical x8) PCIe slot or breakout ribbon. X4 would be a bit of a bottleneck for some GPUs/workloads… Does Strix Halo even support that?

Yep.

I feel the fediverse should lean towards “overly aggressive” when combatting spam, before it takes root, even with all the negatives that brings.

It doesn’t seem that big, right?

If WW was stuck in development hell, cutting Monolith makes sense I guess. PFG only did Multiversus, WB SF seemed to only work on/support mobile games, with no recent credits.

Yeah, but Facebook and Twitter still have the critical mass.

Most of my family’s Trumpism is grassroots, either from their church or other real-world connections.

TBH I don’t know a single person that’s ever used Truth Social, or many that even know what it is. I think it’s more of a niche, not something affecting the masses.