Comment by FuriouslyAdrift
2 hours ago
We're running Kimi 2.8 on a $107k server and getting around 50k tokens per second or better on most things.
We've already saved money compared to last years token cost on Claude/Gemini
2 hours ago
We're running Kimi 2.8 on a $107k server and getting around 50k tokens per second or better on most things.
We've already saved money compared to last years token cost on Claude/Gemini
Are you developing software? Is most of it used on a coding agent? (Like Claude Code or ChatGPT Codex?) If so, what coding agent do you use? If you're not developing software what do you use it for (roughly)?
> We're running Kimi 2.8 on a $107k server
Equipped with what? Is it CPU based inference, a mix...?