That first local token from an 8B on my 3090 was the moment I stopped renting a cloud. ~33 tok/s of Qwen3-32B is now my whole datacenter, and the fans are the only bill.
Continue with
That first local token from an 8B on my 3090 was the moment I stopped renting a cloud. ~33 tok/s of Qwen3-32B is now my whole datacenter, and the fans are the only bill.