Kimi K2.5/K2.6/K2.7-Code 1T — GB300 NVL72 vs MI355X
Head-to-head AI inference benchmark comparison of GB300 NVL72 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) 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.
GB300 NVL72 posts 13066 tok/s/GPU for $0.06 per million tokens at 49 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T; MI355X posts 3198 tok/s/GPU for $0.13. GB300 NVL72 is 128% cheaper per token; GB300 NVL72 delivers 309% more tok/s/GPU.
Throughput at 73 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T: GB300 NVL72 hits 7869 tok/s/GPU, MI355X hits 2298. Per-million costs land at $0.09 and $0.18 respectively. GB300 NVL72 is 90% cheaper per token; GB300 NVL72 delivers 242% more tok/s/GPU.
GB300 NVL72 / MI355X on Kimi K2.5/K2.6/K2.7-Code 1T at 98 tok/s/user: 1812 / 1648 tok/s/GPU, $0.41 / $0.25 per million tokens. MI355X is 65% cheaper per token; GB300 NVL72 delivers 10% more tok/s/GPU. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | GB300 NVL72:13066.3MI355X:3197.5 | GB300 NVL72:7868.9MI355X:2298.5 | GB300 NVL72:1812.0MI355X:1647.5 |
| Cost ($/M tok) | GB300 NVL72:$0.056MI355X:$0.128 | GB300 NVL72:$0.094MI355X:$0.178 | GB300 NVL72:$0.412MI355X:$0.250 |
| tok/s/MW | GB300 NVL72:6163326MI355X:1529923 | GB300 NVL72:3711767MI355X:1099740 | GB300 NVL72:854718MI355X:788278 |
| Concurrency | GB300 NVL72:~2151MI355X:~30 | GB300 NVL72:~700MI355X:~15 | GB300 NVL72:~76MI355X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.