List your company

Max token throughput on 64K/64K serving scenario 8xH100 node 1.0

9.3Max Throughput (K tok/s)gpt-oss-puzzle-88B
3.7885.2196.658.081Feb 12, 2026

Evaluation results

MethodLinks
gpt-oss-puzzle-88BKV precision=KV FP82026.029.3
HyperNova-60BKV precision=KV BF162026.026.9
gpt-oss-puzzle-88BKV precision=KV BF162026.026.5
gpt-oss-120BKV precision=KV FP82026.025.8
gpt-oss-120BKV precision=KV BF162026.024