Hacker News (curated)new | past | comments | ask | show | jobs| show hidden

A detail from the benchmarks in that page is that Nemotron Lightning has good results for a MoE model close to Qwen 27B which is dense. Very interesting considering that Qwen 35B MoE stopped being in Alibaba's plans, and curious if Nemotron is equally capable in other bemchmarks.




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