MiniMax M2.5/M2.7 — MI300X vs MI325X
Head-to-head AI inference benchmark comparison of MI300X (AMD CDNA 3) and MI325X (AMD CDNA 3) on MiniMax M2.5/M2.7. 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 44 tok/s/user interactivity on MiniMax M2.5/M2.7, MI300X delivers 1249 tok/s/GPU at $0.25 per million tokens; MI325X delivers 2007 tok/s/GPU at $0.18. MI325X is 41% cheaper per token; MI325X delivers 61% more tok/s/GPU at this point.
MI300X posts 779 tok/s/GPU for $0.40 per million tokens at 61 tok/s/user on MiniMax M2.5/M2.7; MI325X posts 1044 tok/s/GPU for $0.34. MI325X is 18% cheaper per token; MI325X delivers 34% more tok/s/GPU.
Throughput at 78 tok/s/user on MiniMax M2.5/M2.7: MI300X hits 412 tok/s/GPU, MI325X hits 541. Per-million costs land at $0.75 and $0.67 respectively. MI325X is 12% cheaper per token; MI325X delivers 31% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | MI300X:1248.6MI325X:2007.0 | MI300X:778.8MI325X:1043.8 | MI300X:411.9MI325X:541.1 |
| Cost ($/M tok) | MI300X:$0.250MI325X:$0.177 | MI300X:$0.402MI325X:$0.342 | MI300X:$0.747MI325X:$0.666 |
| tok/s/MW | MI300X:697553MI325X:920648 | MI300X:435091MI325X:478824 | MI300X:230105MI325X:248210 |
| Concurrency | MI300X:~63MI325X:~185 | MI300X:~26MI325X:~71 | MI300X:~11MI325X:~29 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.