The Framework Desktop is a beast • Hacker News Board

Re: The Framework Desktop is a beast

#121

Post by pabs3 » Sun, Aug 10, 2025, 9:21 AM UTC

epistasis wrote: post #54

onli wrote: post #11

Earlier quoted context omitted.

He is still right. It is a desktop PC that is less repairable than all other desktop PCs, from a brand that is known to champion repairability. They had a reason for it, but could've chosen to not create more throwaway things.

I have been continuously baffled by the people that think that soldered on RAM is somehow "throwaway". My last desktop build is eight years old and I have never upgraded the ram. Never will. My next build will have an entirely new motherboard, ram, and GPU, and the last set will end up at the ewaste recycler, because who could I find that wants that old hardware? Soldered RAM, CPU, and GPU, that give space benefits a…

I will take your old builds, because my current PC is from a dumpster and was made in 2013. I can't afford to buy hardware.

Re: The Framework Desktop is a beast

#122

Post by izacus » Sun, Aug 10, 2025, 9:23 AM UTC

Kirth wrote: post #113

I was baffled by the comparison to the M4 Max. Does this mean that recent AMD chips will be performing at the same level, and what does that mean for on-device LLMs? .. or am I misunderstanding this whole ordeal?

Yes, the Strix series of AMD uses a similar architecture as M series with massive memory bandwidth and big caches.

That results in significantly better performance.

Re: The Framework Desktop is a beast

#123

Post by biehl » Sun, Aug 10, 2025, 9:23 AM UTC

Kirth wrote: post #113

I was baffled by the comparison to the M4 Max. Does this mean that recent AMD chips will be performing at the same level, and what does that mean for on-device LLMs? .. or am I misunderstanding this whole ordeal?

I think DHH compares them because they are both the latest, top-line chips. I think DHHs benchmarks show that they have different performance characteristics. But DHHs favorite benchmark favors whatever runs native linux and docker.

For local LLM the higher memory bandwith of M4 Max makes it much more performant.

Arstechnica has more benchmarks for non-llm things https://arstechnica.com/gadgets/2025/08/review-framework-des...

Re: The Framework Desktop is a beast

#124

Post by sliken » Sun, Aug 10, 2025, 9:27 AM UTC

mixmastamyk wrote: post #91

fmajid wrote: post #82

I cancelled my Framework Desktop order and ordered a HP Z2 Mini G1a instead, the goal being to replace my Mac Studio as I've had it with Apple's arrogance and lousy software quality. The HP is much smaller, has ECC RAM and 10G Ethernet. Significantly more expensive, however.

Was scoffing at HP, but then you got my attention with ECC RAM. Looks nice as well.

Keep scoffing, it's not real end to end ECC, just "link" ecc, which is just part of the chip -> CPU pipeline.

So it's not full ECC like servers have with dimms with a multiple of 9 chips with ECC protecting everything from the dimms to the CPU.

Keep in mind the ram is inside the strix halo package, not something HP has control over.

Re: The Framework Desktop is a beast

#125

Post by sliken » Sun, Aug 10, 2025, 9:32 AM UTC

Jtsummers wrote: post #2

> In some ways, the Framework Desktop is a curious machine. Desktop PCs are already very user-repairable! So why is Framework even bringing their talents to this domain? In the laptop realm, they're basically alone with that concept, but in the desktop space, it's rather crowded already. Yet it somehow still makes sense. And even more curious, Framework Desktop is deliberately less repairable than their laptops. They…

Dunno, nice, quiet, small machine, using standard parts (power supply, motherboard, etc).

If you want the high memory bandwidth get the strix halo, if not get any normal PC. Sure apple has the bandwidth as well, and also soldered memory as well.

If you want dimms and you want the memory bandwidth get a threadripper (4 channel), siena (6 channel), thread ripper pro (8 channel), or Epyc (12 channel). But be prepared to double your power (at least), quadruple your space, double your cost, and still not have a decent GPU.

Re: The Framework Desktop is a beast

#126

Post by suspended_state » Sun, Aug 10, 2025, 9:44 AM UTC

beeflet wrote: post #31

suspended_state wrote: post #13

Earlier quoted context omitted.

> They soldered on the RAM. Which makes it a very strange entry for a brand marketing itself as the DIY dream This was also my first thought when discovering this new model, but I think it was a pragmatic design decision. The questions you should ask yourself are: - which upgradable memory module format could be used with the same speed and bandwidth as the soldered in solution, - if this solution exists, how much wo…

>which upgradable memory module format could be used with the same speed and bandwidth as the soldered in solution CAMM perhaps? The modular memory is important, because they are selling them to two different markets: gamers that want a small powerful desktop, and people running LLMs at home. The modularity of the RAM allows you to convert the former into the latter at a later date, so it seems pretty critical to me.…

You should do what better fit your usecase.

I don't know how large is framework's market, nor how deep their pockets are, which condition their ability to produce 2 different models.

It's clear that a modular design is preferable, hopefully once a standard emerges they will use it in their next devices. Perhaps framework will help in that process, but I don't know if they can afford to put up with the initial costs, particularly in a market they don't have a strong foothold yet.

Re: The Framework Desktop is a beast

#127

Post by cdavid » Sun, Aug 10, 2025, 9:45 AM UTC

Kirth wrote: post #113

I was baffled by the comparison to the M4 Max. Does this mean that recent AMD chips will be performing at the same level, and what does that mean for on-device LLMs? .. or am I misunderstanding this whole ordeal?

I was surprised at previous comparison on omarchy website, because apple m* work really well for data science work that don't require GPU.

It may be explained by integer vs float performance, though I am too lazy to investigate. A weak data point, using a matrix product of N=6000 matrix by itself on numpy:

  - SER 8 8745, linux: 280 ms -> 1.53 Tflops (single prec)
  - my m2 macbook air: it is ~180ms ms -> ~2.4 Tflops (single prec)

This is 2 mins of benchmarking on the computers I have. It is not apple to orange comparison (e.g. I use the numpy default blas on each platform), but not completely irrelevant to what people will do w/o much effort. And floating point is what matters for LLM, not integer computation (which is what the ruby test suite is most likely bottlenecked by)

Re: The Framework Desktop is a beast

#128

Post by sliken » Sun, Aug 10, 2025, 9:45 AM UTC

beeflet wrote: post #35

sethops1 wrote: post #3

Earlier quoted context omitted.

The RAM is soldered on all Halo Strix platforms because physics is getting in the way. With pluggable DIMMs the memory bandwidth would be halved, at best.

Why not make a platform with a greater number of channels

Sure, you could. The design would do something like:

We need a bigger memory controller.

To get more traces to the memory controller We need more pins on the CPU.

Now need a bigger CPU package to accommodate the pins.

Now we need a motherboard with more traces, which requires more layers, which requires a more expensive motherboard.

We need a bigger motherboard to accommodate the 6 or 8 dimm sockets.

The additional traces, longer traces, more layers on the motherboard, and related makes the signalling harder, likely needs ECC or even registered ECC.

We need a more expensive CPU, more expensive motherboard, more power, more cooling, and a larger system. Congratulations you've reinvented threadripper (4 channel), siena (6 channel), Threadripper pro (8 channel), or epyc (12 channel). All larger, more expensive more than 2x the power, and is likely to be in a $5-$15k workstation/server not a $2k framework desktop the size of a liter of milk or so.

Re: The Framework Desktop is a beast

#129

Post by wiseowise » Sun, Aug 10, 2025, 9:51 AM UTC

mtzet wrote: post #119

wiseowise wrote: post #117

Earlier quoted context omitted.

Supporting OSS and repairable hardware?

A normal desktop with non-soldered components is more repairable, cheaper and can also run on stock Linux? The only selling point is the form factor and a massive amount of GPU memory, but a dGPU offers more raw compute.

> with non-soldered components is more repairable

This is literally the limitation of the platform. Why even bring that up? Framework took a part made by AMD and put in their devices.

Re: The Framework Desktop is a beast

#130

Post by wiseowise » Sun, Aug 10, 2025, 9:53 AM UTC

mschild wrote: post #118

wiseowise wrote: post #117

Earlier quoted context omitted.

Supporting OSS and repairable hardware?

OSS is fair. From the product page I don't see how that mainboard is more repairable than a typical ITX one though. As far as I can tell, you also cannot change the CPU on it so even less than a typical desktop mainboard.

By buying their devices you directly support company and mission that they're on. I'm not a diehard OSS supporter (Mac user here), but I consider buying The Framework Desktop just to support the company over, say, Dell or HP.