Live data from Hacker News

A 10 year old Xeon is all you need

point.free

291–300 of 301 posts

Re: A 10 year old Xeon is all you need

#291
post #267

Earlier quoted context omitted.

I bought a renewed 2x E5-2690v4 server (28c/56t) 128gb on amazon for under $500 2 years ago (28c/56t) dell T7810 search amazon for "chia farming" ...and scroll past chia seeds :) now same machine is 2.5x the price https://www.amazon.com/dp/B095TRGCSX but way cheaper than current ddr5 machines

> now same machine is 2.5x the price 2.5x?! I have a bunch of older Haswell servers I got for free that are rotting away in my garage. I had initially thought of stripping out the ECC DDR4, but now I'm wondering if I'll get takers on Marketplace...

Honestly, if someone can actually use them (as demonstrated by paying the price+shipping) then they would probably have a better home with that person.

Re: A 10 year old Xeon is all you need

#292

Earlier quoted context omitted.

There were several V4 Xeon models that supported DDR3 AND DDR4 simultaneously. If you had a motherboard with an X79 chipset it would (sometimes) work properly.

I am not aware of any commercial vendor shipping v3/v4 boards with DDR3. I have a couple hundred Supermicro systems that are stuck on v2 CPUs with DDR3...

Get a 2696 v4 or 2686 v4 and a X79 motherboard and you should be able to use DDR3.

Re: A 10 year old Xeon is all you need

#293

Either they have a E5-2620 V2 from 13 years ago, or they have DDR4, not DDR3. The V3 and V4 only support DDR4.

No they don’t. Models ending in 6 have DDR3 controller.

For example

E5-2696 v3/v4 E5-2686 v3/v4 E5-2666 v3/v4

also

2673 v3/v4 2678 v3/v4

as well as E5 2629 v3 E5 2649 v3 E5 2669 v3

Re: A 10 year old Xeon is all you need

#294

The E5-2620 v4 is great. Have been using it for 10 years now. Wanted to upgrade until I saw current prices. I have 64 GB ddr4. Paired it with rx 9060 xt 16 GB and games run as fast as ever. Perhaps the cpu is a slight bottleneck in DOOM The Dark Ages, but i'm at 60 fps, so no problem. Light llm on the gpu is a nobrainer, and it's cool to see that things can be tuned to run ok on the cpu. I bought 2667 v4 a month ago…

> The E5-2620 v4 is great. Have been using it for 10 years now. 10 years? Damn, that is a long time. I always assumed that heat-induced damage will kill a CPU after a certain amount of time (5-7 years). Am I wrong here? I assume yes. Or are CPUs must stronger/tougher than the bad old days?

I have a couple PCs running with CPUs from 15 years ago with tons of power on time. Never heard of a CPU dying from age before.

Re: A 10 year old Xeon is all you need

#295
post #193

Earlier quoted context omitted.

And like Google and Meta, these companies are going to morph into advertising giants. Advertising is an economic black hole and it eats everything that comes close.

Embedding ads in LLM responses is something researchers are having a lot of trouble figuring out right now. I have seen the results of some early attempts. It fails in such hilarious ways that all these companies are scared of productizing it. But once someone does it, the taboo is broken and everyone else will follow suit immediately.

Yet they managed to get a fake disease into them.

Re: A 10 year old Xeon is all you need

#296
post #287

Earlier quoted context omitted.

But you're mentioning several things that predate the current LLM craze and belong to the ML domain. These mostly benefit from GPUs but often have much lower hardware requirements. I'm talking specifically about the moat of LLM providers.

Sure, but all fall under the same marketing umbrella. Ad/marketing manipulation are exceptionally well done with LLMs in particular. If you asked someone if drone auto targeting/image recognition or data analysis was ‘AI’, 99% of the time they’ll say yes.

It doesn't matter what people call it. We're talking about maintaining a moat with extremely demanding use cases, and the extremely demanding range shrinks every few months.

Re: A 10 year old Xeon is all you need

#297
post #287

Earlier quoted context omitted.

Sure, but all fall under the same marketing umbrella. Ad/marketing manipulation are exceptionally well done with LLMs in particular. If you asked someone if drone auto targeting/image recognition or data analysis was ‘AI’, 99% of the time they’ll say yes.

It doesn't matter what people call it. We're talking about maintaining a moat with extremely demanding use cases, and the extremely demanding range shrinks every few months.

I’m saying most of the moat was never there to begin with, and the rest is mostly immaterial to the bulk of the use cases.

Re: A 10 year old Xeon is all you need

#299
the surge of articles on using decommissioned datacentre hw to run LLMs lately, is more of a symptom of the times than their viability. back when intel had a monopoly on cpu and would refuse to give consumers more than four cores, the old xeon route was popular for a different reason.

memory is the bottleneck here (capacity, or rather speed). before you run out to set up your own, try to rather squeeze out the most of your existing hardware. if you are a lucky owner of a lot of cheap memory, you are already in luck. otherwise LM studio allows you to split memory between your gpu and system memory. avoid MoE models or even consider tensor parallelism between the onboard gpu and dedicated one before going for more hardware.

there is little to no benefit for using a specific quantization for your models, so go crazy and test out whatever can easily run for you.

Re: A 10 year old Xeon is all you need

#300

Well, lets get started. I have 4 of those machines, and they are Two dual processor. They all had 32GB of ram, so now I have two with 64GB, and two with zero. They all hand stock K5000s, now how two have two cards. I stripped the uni processors ram and video cards, and put those into the dual procs. They have 256Gb SSDs, and two 1TB disk drives. One machine has 8Gb of VRam across two cards. Dual processors are 8Cx2 a…

That’s because all of that hardware probably dates back to when Steve Jobs roamed the planet.
Post reply on HN