I’ve a 128GB m3 max MacBook Pro. Running the gpt oss model on it via lmstudio once the context gets large enough the fans spin to 100 and it’s unbearable.
My RTX 5090 can fit OSS-20B but it’s a bit underwhelming, and for $3000 if I didn’t also use it for gaming I’d have been pretty disappointed.
[1] https://www.idealo.de/preisvergleich/OffersOfProduct/2063285...