News for hackers. Stuff that matters.
Re:Kimi K3, Qwen 3.8, and Anthropic's (Potential) Unravelling by wongarsu on Monday July 20, 2026 @12:54PM (#48981452)
While running the model at 9000 tokens/s is the more flashy demo, I imagine running 1000 concurrent requests at 150 tokens/s each is the much more achievable goal
Re:Kimi K3, Qwen 3.8, and Anthropic's (Potential) Unravelling by LarsDu88 on Monday July 20, 2026 @02:14PM (#48982641)
At 9000 tokens/s you could interleave a lot of requests so long as pre-fill is also fast. It really depends on how much you need to keep sessions open to take advantage of KV caching
Re:Kimi K3, Qwen 3.8, and Anthropic's (Potential) Unravelling by wyre on Monday July 20, 2026 @01:39PM (#48982112)
It depends. If I was running a model locally I would much prefer 9000 t/s. If I was running an inference company, obv 1000 concurrent requests at 150 t/s is preferable.