Exactly the kind of breakdown I was hoping to see. Thanks.
And we can quickly see that the real problem is not the models, but HW to run them. You can build whole Enterprise on Gemma 4 31B full precision without significant problems. If you can afford not to lobotomise it by quantisation.
alt Hacker News
And we can quickly see that the real problem is not the models, but HW to run them. You can build whole Enterprise on Gemma 4 31B full precision without significant problems. If you can afford not to lobotomise it by quantisation.