MiniMax M2.5/M2.7 · Chip comparison
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 30 tok/s/user interactivity on MiniMax M2.5/M2.7, MI300X delivers 1,570 tok/s/chip at $0.17 per million tokens; MI325X delivers 2,916 tok/s/chip at $0.10. MI325X is 38% cheaper per token; MI325X delivers 86% more tok/s/chip at this point.
MI300X posts 1,412 tok/s/chip for $0.19 per million tokens at 48 tok/s/user on MiniMax M2.5/M2.7; MI325X posts 2,106 tok/s/chip for $0.15. MI325X is 22% cheaper per token; MI325X delivers 49% more tok/s/chip.
Throughput at 66 tok/s/user on MiniMax M2.5/M2.7: MI300X hits 1,086 tok/s/chip, MI325X hits 1,433. Costs per million tokens land at $0.24 and $0.21 respectively. MI325X is 12% cheaper per token; MI325X delivers 32% more tok/s/chip. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | MI300X1,570MI325X2,916 | MI300X1,412MI325X2,106 | MI300X1,086MI325X1,433 |
| Cost ($/M tok) | MI300X$0.17MI325X$0.10 | MI300X$0.19MI325X$0.15 | MI300X$0.24MI325X$0.21 |
| tok/s/MW | MI300X1,129,783MI325X1,725,192 | MI300X1,015,827MI325X1,246,204 | MI300X781,024MI325X847,801 |
| Concurrency | MI300X~20MI325X~22 | MI300X~7MI325X~10 | MI300X~4MI325X~5 |