← Back to context Comment by esafak 5 hours ago But in 10x the time? 3 comments esafak Reply verdverm 5 hours ago that's a matter of hardware, Cerebras reports 1500 tok/shttps://inference-docs.cerebras.ai/models/qwen-3.8-27b msikora 4 hours ago Input $0.99 Output $1.49That times 5 is steep! verdverm 4 hours ago Getting close to 80 tok/s on the dgx spark with NVFP4https://spark-arena.com/leaderboard(you'll have to filter model yourself, no query params)
verdverm 5 hours ago that's a matter of hardware, Cerebras reports 1500 tok/shttps://inference-docs.cerebras.ai/models/qwen-3.8-27b msikora 4 hours ago Input $0.99 Output $1.49That times 5 is steep! verdverm 4 hours ago Getting close to 80 tok/s on the dgx spark with NVFP4https://spark-arena.com/leaderboard(you'll have to filter model yourself, no query params)
msikora 4 hours ago Input $0.99 Output $1.49That times 5 is steep! verdverm 4 hours ago Getting close to 80 tok/s on the dgx spark with NVFP4https://spark-arena.com/leaderboard(you'll have to filter model yourself, no query params)
verdverm 4 hours ago Getting close to 80 tok/s on the dgx spark with NVFP4https://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)