> You can do local AI inference and get Claude Opus-level performance (Kimi K2.5...

		potamic 5 days ago \| parent \| context \| favorite \| on: I tried building my startup entirely on European i... > You can do local AI inference and get Claude Opus-level performance (Kimi K2.5) over a cluster of Mac Studios with Exo.Labs Does it do distributed inference? What kinda token speeds do you get?

		help