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

Set up mmap properly and you can evaluate small/medium MoE models (such as the recent A3B from Qwen) on most ordinary hardware, they'll just be very slow. But if you're willing to wait you can get a feel for their real capabilities, then invest in what it takes to make them usable. (Usually running them on OpenRouter will be cheaper than trying to invest in your own homelab: even if you're literally running them on a 24/7 basis, the break even point compared to a third-party service is too unrealistic.)
 help



Subjectively, but with tests using identical prompts, I find the quality of qwen3.5 122b below claude haiku by as much as claude haiku is below claude sonnet for software design planning tasks. I have yet to try a like-for-like test on coding.



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

Search: