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

Which conveniently fits on one 8xH100 machine. With 100-200 GB left over for overhead, kv-cache, etc.


The unit economics seem pretty rough though. You're locking up 8xH100s for the compute of ~32B active parameters. I guess memory is the bottleneck but hard to see how the margins work on that.


Yes, it only makes sense economically if you have batching over many users.




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

Search: