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

14B even at Q4 isn't realistic for coding on a single 12GB RTX 3060. Token speed is too slow. After all they are dense models. You aren't getting a good MoE model under 30B. You can do OCR, STT, TTS really well and for LLMs, good use cases are classification, summarization and extraction with <10B models.


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.


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

Search: