Kimi K2.5/K2.6 1T · GPU comparison

Kimi K2.5/K2.6 1T — GB200 NVL72 vs MI355X

Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) 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.

Setting 47 tok/s/user as the target on Kimi K2.5/K2.6 1T, GB200 NVL72 produces 4569 tok/s/GPU ($0.13 per million tokens) and MI355X produces 707 ($0.58). GB200 NVL72 is 334% cheaper per token; GB200 NVL72 delivers 546% more tok/s/GPU.

At 69 tok/s/user interactivity on Kimi K2.5/K2.6 1T, GB200 NVL72 delivers 1370 tok/s/GPU at $0.45 per million tokens; MI355X delivers 548 tok/s/GPU at $0.75. GB200 NVL72 is 67% cheaper per token; GB200 NVL72 delivers 150% more tok/s/GPU at this point.

GB200 NVL72 posts 728 tok/s/GPU for $0.85 per million tokens at 91 tok/s/user on Kimi K2.5/K2.6 1T; MI355X posts 419 tok/s/GPU for $0.98. GB200 NVL72 is 15% cheaper per token; GB200 NVL72 delivers 74% more tok/s/GPU. (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.)

View performance-per-dollar view →

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/gpu)
GB200 NVL72:4569.1MI355X:706.9
GB200 NVL72:1370.0MI355X:547.9
GB200 NVL72:728.1MI355X:418.8
Cost ($/M tok)
GB200 NVL72:$0.134MI355X:$0.582
GB200 NVL72:$0.448MI355X:$0.750
GB200 NVL72:$0.854MI355X:$0.982
tok/s/MW
GB200 NVL72:2175765MI355X:266771
GB200 NVL72:652400MI355X:206736
GB200 NVL72:346731MI355X:158047
Concurrency
GB200 NVL72:~1131MI355X:~32
GB200 NVL72:~430MI355X:~17
GB200 NVL72:~155MI355X:~9

Inference Performance

Inference performance metrics across different models, hardware configurations, and serving parameters.