Kimi K2.5/K2.6 1T — MI300X vs MI325X
Head-to-head AI inference benchmark comparison of MI300X (AMD CDNA 3) 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.
MI300X posts 117 tok/s/GPU for $2.63 per million tokens at 24 tok/s/user on Kimi K2.5/K2.6 1T; MI325X posts 144 tok/s/GPU for $2.50. MI325X is 5% cheaper per token; MI325X delivers 22% more tok/s/GPU.
Throughput at 32 tok/s/user on Kimi K2.5/K2.6 1T: MI300X hits 97 tok/s/GPU, MI325X hits 131. Per-million costs land at $3.22 and $2.72 respectively. MI325X is 18% cheaper per token; MI325X delivers 35% more tok/s/GPU.
MI300X / MI325X on Kimi K2.5/K2.6 1T at 40 tok/s/user: 70 / 89 tok/s/GPU, $4.44 / $4.03 per million tokens. MI325X is 10% cheaper per token; MI325X delivers 26% more tok/s/GPU. (Numbers reflect the default 1k/1k · int4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | MI300X:117.3MI325X:143.6 | MI300X:97.2MI325X:131.1 | MI300X:70.4MI325X:88.7 |
| Cost ($/M tok) | MI300X:$2.627MI325X:$2.495 | MI300X:$3.224MI325X:$2.721 | MI300X:$4.441MI325X:$4.028 |
| tok/s/MW | MI300X:65505MI325X:65880 | MI300X:54323MI325X:60121 | MI300X:39352MI325X:40676 |
| Concurrency | MI300X:~20MI325X:~24 | MI300X:~12MI325X:~17 | MI300X:~7MI325X:~9 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.