MiniMax M2.5/M2.7 — MI325X vs MI355X
Head-to-head AI inference benchmark comparison of MI325X (AMD CDNA 3) and MI355X (AMD CDNA 4) 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.
Near the low end of the 27–104 tok/s/user interactivity band, at 46 tok/s/user on MiniMax M2.5/M2.7: MI325X runs 1643 tok/s/GPU at $0.22/M tokens, MI355X runs 3584 at $0.12/M. MI355X is 88% cheaper per token; MI355X delivers 118% more tok/s/GPU.
Setting 65 tok/s/user as the target on MiniMax M2.5/M2.7, MI325X produces 757 tok/s/GPU ($0.48 per million tokens) and MI355X produces 1259 ($0.33). MI355X is 43% cheaper per token; MI355X delivers 66% more tok/s/GPU.
At 85 tok/s/user interactivity on MiniMax M2.5/M2.7, MI325X delivers 325 tok/s/GPU at $1.09 per million tokens; MI355X delivers 710 tok/s/GPU at $0.58. MI355X is 88% cheaper per token; MI355X delivers 119% more tok/s/GPU at this point. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | MI325X:1642.6MI355X:3584.5 | MI325X:757.2MI355X:1258.9 | MI325X:324.7MI355X:710.0 |
| Cost ($/M tok) | MI325X:$0.217MI355X:$0.115 | MI325X:$0.479MI355X:$0.334 | MI325X:$1.094MI355X:$0.581 |
| tok/s/MW | MI325X:753479MI355X:1352629 | MI325X:347355MI355X:475054 | MI325X:148934MI355X:267921 |
| Concurrency | MI325X:~147MI355X:~256 | MI325X:~38MI355X:~24 | MI325X:~16MI355X:~9 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.