[dudefeliciano]

what hardware are you using those on? Is it still prohibitively expensive to self-host a model that gives decent outputs (sorry my last experience has been underwhelming with llama a while back)

[sliken]

I'm tinkering with gemma 3 27B on a last gen 12 core ryzen. I get 5 tokens/sec.

[archerx]

I have an AMD 6700 XT card with 12gb of VRAM and a 24 core cpu with 48gigs of ram. This is the bare minimum,