SOTA · inference tokens/sec/$ · LLaMA-3-70B, 8×H200, 2K ctx, BF16
$/hr from signed cloud price feed; tokens/sec measured on the sealed rerun cluster.
loading...
loading...
click to expand · verify re-checks sigs + inclusion
Systems · live
Inference, training, serving, orchestration. All data from .
SOTA · inference tokens/sec/$ · LLaMA-3-70B, 8×H200, 2K ctx, BF16
$/hr from signed cloud price feed; tokens/sec measured on the sealed rerun cluster.