Kimi K2.5/K2.6 1T — GB200 NVL72 vs MI325X
Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and MI325X (AMD CDNA 3) on Kimi K2.5/K2.6 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.
GB200 NVL72: 1855 tok/s/GPU, $0.33 per million tokens at 60 tok/s/user on Kimi K2.5/K2.6 1T. MI325X is unmeasured here.
At 103 tok/s/user on Kimi K2.5/K2.6 1T, GB200 NVL72 delivers 584 tok/s/GPU at $1.18 per million tokens; MI325X hasn't been benchmarked at this target.
GB200 NVL72 hits 133 tok/s/GPU for $4.69 per million tokens at 146 tok/s/user on Kimi K2.5/K2.6 1T. No MI325X data at this operating point. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | GB200 NVL72:1854.8MI325X:— | GB200 NVL72:584.3MI325X:— | GB200 NVL72:133.2MI325X:— |
| Cost ($/M tok) | GB200 NVL72:$0.328MI325X:— | GB200 NVL72:$1.180MI325X:— | GB200 NVL72:$4.687MI325X:— |
| tok/s/MW | GB200 NVL72:883236MI325X:— | GB200 NVL72:278250MI325X:— | GB200 NVL72:63416MI325X:— |
| Concurrency | GB200 NVL72:~667MI325X:— | GB200 NVL72:~116MI325X:— | GB200 NVL72:~13MI325X:— |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.