News for hackers. Stuff that matters.
Re:Grok3 Launch by nomel on Thursday February 20, 2025 @01:08PM (#43118066)
They said 1.5 tokens/second. 1 mil tokens is 667k seconds is 185 hours per million tokens. 1kW * 185hr * $0.45/kWh = $80 per million tokens. Again, assuming 1kW, which may be high (or low). The cost of the physical computation is electricity cost.
Re:Grok3 Launch by CyberDildonics on Thursday February 20, 2025 @01:36PM (#43118357)
They said it has a crappy GPU, the whole computer probably only uses 200 - 250 watts.
Re:Grok3 Launch by nomel on Thursday February 20, 2025 @03:49PM (#43119991)
No way. 768GB of ram will have significant power draw. DDR4 (which this probably is) is something like 3W/8GB. That's > 250W alone.

So, say 500W. That's, for me in my expensive electricity city, $40/million tokens, with the pretty severe rate limit of 5600 tokens/hours.

If you're in Texas, that would be closer to $10/million tokens! Now you're at the same price as GPT-4o.

Re:Grok3 Launch by menaerus on Friday February 21, 2025 @03:42AM (#43125432)
But you can run and experiment with any model of your liking. And your data does not leave your desktop environment. You can build services. I don't think anybody doing this is doing it to save $20 a month.
Re:Grok3 Launch by nomel on Friday February 21, 2025 @02:43PM (#43132011)
Yes. I was only making a monetary comparison.

Related, you can get a whole lot of cloud computing for $2k, for those same experiments, on much faster hardware.

But yes, the data stays local. And, it's fun.

This comment chain is pretty funny.