Kimi K2.5/K2.6 1T — B300 vs MI355X
Head-to-head AI inference benchmark comparison of B300 (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.
At 54 tok/s/user interactivity on Kimi K2.5/K2.6 1T, B300 delivers 1059 tok/s/GPU at $0.61 per million tokens; MI355X delivers 632 tok/s/GPU at $0.66. B300 is 8% cheaper per token; B300 delivers 68% more tok/s/GPU at this point.
B300 posts 925 tok/s/GPU for $0.70 per million tokens at 74 tok/s/user on Kimi K2.5/K2.6 1T; MI355X posts 516 tok/s/GPU for $0.80. B300 is 13% cheaper per token; B300 delivers 79% more tok/s/GPU.
Throughput at 94 tok/s/user on Kimi K2.5/K2.6 1T: B300 hits 910 tok/s/GPU, MI355X hits 396. Per-million costs land at $0.72 and $1.04 respectively. B300 is 45% cheaper per token; B300 delivers 130% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B300:1059.3MI355X:631.8 | B300:925.0MI355X:516.1 | B300:910.0MI355X:396.0 |
| Cost ($/M tok) | B300:$0.612MI355X:$0.658 | B300:$0.704MI355X:$0.797 | B300:$0.715MI355X:$1.040 |
| tok/s/MW | B300:488139MI355X:238416 | B300:426266MI355X:194767 | B300:419364MI355X:149436 |
| Concurrency | B300:~40MI355X:~24 | B300:~26MI355X:~14 | B300:~21MI355X:~9 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.