Give @LottoLabs a follow if you are not already
He is building https://t.co/h8a7ALYyCY, crowdsourced LLM benchmark results and performance profilings
Very very cool
This. Especially when the whole machine hangs instead of OOMing when my agent accidentally loads too many models into memory
(lmk if there is a firmware update or sth that fixes this on the spark now, creating a cgroup doesn’t work)
https://t.co/1IINcugVN7