I've run it with a large context window on 256GB ram + 4090. It wasn't super fas... | Hacker News

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

kybernetikos 35 days ago | parent | context | favorite | on: Muse Glimmer: 30B-parameter model optimized for al...

I've run it with a large context window on 256GB ram + 4090. It wasn't super fast, but it was manageable and it completed the tasks I gave it well.

xiconfjs 35 days ago [–]

How many tps and size of ctx?

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