← Back to context Comment by KerrAvon 2 hours ago We're on the cusp of Kimi K3 becoming usable on sub-10k hardware.https://github.com/gavamedia/deltafin 2 comments KerrAvon Reply edot 2 hours ago 14 seconds per token? Not tokens per second. Seconds per token? That’s nowhere near the cusp! ekidd 2 hours ago For values of "usable" that include "14.6 seconds/token". It's a cool accomplishment! And newer hardware would speed it up some. But I think I'd want something a bit faster before declaring it usable in practice.
edot 2 hours ago 14 seconds per token? Not tokens per second. Seconds per token? That’s nowhere near the cusp!
ekidd 2 hours ago For values of "usable" that include "14.6 seconds/token". It's a cool accomplishment! And newer hardware would speed it up some. But I think I'd want something a bit faster before declaring it usable in practice.
14 seconds per token? Not tokens per second. Seconds per token? That’s nowhere near the cusp!
For values of "usable" that include "14.6 seconds/token". It's a cool accomplishment! And newer hardware would speed it up some. But I think I'd want something a bit faster before declaring it usable in practice.