I wonder if it's better in Antigravity? Their harness might help some? I haven't tested Argon out.

I'm talking specifically about using it in Antigravity CLI.

They're training on trillions of tokens. Isn't it highly unlikely that the under a thousand tokens about your "new science" would surface in a meaningful way?

The fact that it's showing Palo Alto / Menlo Park is disconcerting, but not surprising. Very strange.

Is it definitely out of the question?

https://openai.com/index/cerebras-partnership/

> 5060

I think you're referring to a 5060Ti 16GB, yes?

32k context is easily done there. 64k can work with a more aggressive quant, but you lose a bit of speed.

Yeah 16gb. For longer context, a 3bit quant is needed. Yes it’s tight on a 16gb card - can’t wait for the bubble to pop so hardware prices fall.

But I don’t quite follow you - how does a more aggressive quant slow it down? Less bits per token means faster inference not slower.