But in 10x the time?
that's a matter of hardware, Cerebras reports 1500 tok/s
https://inference-docs.cerebras.ai/models/qwen-3.8-27b
Input $0.99 Output $1.49
That times 5 is steep!
Getting close to 80 tok/s on the dgx spark with NVFP4
https://spark-arena.com/leaderboard
(you'll have to filter model yourself, no query params)
that's a matter of hardware, Cerebras reports 1500 tok/s
https://inference-docs.cerebras.ai/models/qwen-3.8-27b
Input $0.99 Output $1.49
That times 5 is steep!
Getting close to 80 tok/s on the dgx spark with NVFP4
https://spark-arena.com/leaderboard
(you'll have to filter model yourself, no query params)