I fucking knew it and never trusted them.

Any seller charges 50%+ margin on anything.

Back to SVN then? Noted.

It can be predatory pricing that will bite us later.

How exactly will downloaded gguf files bite me later?

Is it going to shut the laptop's lid when i'm not looking and pinch my fingers?

It really can't be when the models are open weights and there's zero lock-in for inference providers.

ZX's audio and video systems are two things that I never missed.

We didn't!

"Esoteric cypher that no one has seriously tried to break" lol

It's military comms traffic from WW2, encrypted by machine named Enigma. Back in 1940's it was like breaking SSL today, with only difference that they actually could (kinda) break Enigma.

You don’t have to be patronizing it’s esoteric because they had a new key every single day so it’s very possible no one has looked at one of the millions of messages the Germans sent over the entire period of the war.

The main gotcha for local models is insane hardware requirements.

Even for $10K you get mediocre performance.

This situation has improved quite a bit recently, Qwen Flash Next will run on a $4000 PC and can reliably implement small features on its own (feels comparable to Opus 4.5). It's a bit slow but pretty effective.

Less. Probably 2-3K if you build right. Qwen 3.8 27B on constrained tasks is Opus 4.6-ish to me, it just doesn’t know enough, but when task is laid out just gets it done.

Comes down to how much of the ambiguity we expect out of the model.

What would you build? Flash Next on 128GB works ok, 3.8 27B might technicially work on less but it's just too slow at least on current APU style chips. I'm curious about the non-NVIDIA 32GB discrete GPU options but I haven't tried yet.

Flash next only needs 64GB for core model inference. If you really wanted it.

Need 64GB vram, 900+ GB/s speed, and a lot of system ram (128GB). Seems feasible. Hmm.

Maybe older GPUs work.

128GB on a Ryzen 395 is enough but not by a lot. Around 90GB for weights plus 10GB to 20GB for KV cache and checkpoints. I don't know about 64GB of VRAM for less than around $2500 by itself.

Tesla V100? Would have to be a 3-ish bit quant in 64GB ram

I think this is worth revisiting once we get some solid 3rd party numbers from the new mac studio ultras, which admittedly are a bit over $10k with a 2tb ssd + 256gb ram. I think I'd be seriously considering it if I had a $200/month subscription of some kind.

Not anymore. Qwen 3.8 27B is so great that 5k investment gives you excellent speed and quality.

Yeah, space exploration/colonization can be only made by species that live a million years, or can pass the same goal across many generations forward.

Maybe it's the answer to Fermi paradox: aliens are all around, we're just too fast for them to communicate.

Relativity fixes that a little, you don't need to go light speed to make it all over the place within your lifetime, it's the observers who sent you off that will never reap the fruits of their effort.