Comment by tornikeo
13 hours ago
On paper. There's huge financial incentive to quantize the crap out of a good model to save cash after you've hooked in subscriptions.
13 hours ago
On paper. There's huge financial incentive to quantize the crap out of a good model to save cash after you've hooked in subscriptions.
And there’s an incentive to publish evidence of this to discourage it, do you have any?
Models aren't just big bags of floats you imagine them to be. Those bags are there, but there's a whole layer of runtimes, caches, timers, load balancers, classifiers/sanitizers, etc. around them, all of which have tunable parameters that affect the user-perceptible output.
There really always is a man behind the curtain eh?
2 replies →
There's this[1]. Model providers have a strong incentive to switch (a part of) their inference fleet to quantized models during peak loads. From a systems perspective, it's just another lever. Better to have slightly nerfed models than complete downtime.
[1]: https://marginlab.ai/trackers/claude-code/
So - as the charts say - no statistical difference?
Isn't this link am argument against the point you are making?
1 reply →
Anybody with more than five years in the tech industry has seen this done in all domains time and again. What evidence you have AI is different, which is the extraordinary claim in this case...
Or just change the reasoning levels.