Kimi K2.5/K2.6/K2.7-Code 1T · Chip comparison

Kimi K2.5/K2.6/K2.7-Code 1T — GB200 NVL72 vs H200

Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and H200 (NVIDIA Hopper) on Kimi K2.5/K2.6/K2.7-Code 1T. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.

At 64 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, GB200 NVL72 delivers 8,980 tok/s/chip at $0.058 per million tokens; H200 hasn't been benchmarked at this target.

GB200 NVL72 hits 1,545 tok/s/chip for $0.33 per million tokens at 103 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T. No H200 data at this operating point.

GB200 NVL72: 733 tok/s/chip, $0.70 per million tokens at 141 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T. H200 is unmeasured here. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)

View performance per dollar →

Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.

Metric
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Throughput (tok/s/chip)
GB200 NVL728,980H200—
GB200 NVL721,545H200—
GB200 NVL72733H200—
Cost ($/M tok)
GB200 NVL72$0.058H200—
GB200 NVL72$0.33H200—
GB200 NVL72$0.70H200—
tok/s/MW
GB200 NVL724,801,979H200—
GB200 NVL72826,425H200—
GB200 NVL72391,932H200—
Concurrency
GB200 NVL72~1,203H200—
GB200 NVL72~167H200—
GB200 NVL72~27H200—