Dual 3060s run 24B Q6 and 32B Q4 at ~15 tok/sec. That's fast enough to be usable... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		suprjami 46 days ago \| parent \| context \| favorite \| on: Quantization from the Ground Up Dual 3060s run 24B Q6 and 32B Q4 at ~15 tok/sec. That's fast enough to be usable. Add a third one and you can run Qwen 3.5 27B Q6 with 128k ctx. For less than the price of a 3090.

rdos 33 days ago [–]

Sure, two 3060 can pull usable performance on an usable LLM, but a single one can't (yet).

> 3x RTX 3060 less tgab the price of a 3090

Interesting, here it is around the same. 200-250€ for a used 12GB 3060 and 600-800 for a used 3090€.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact