MiniMax M2.5/M2.7 · Chip comparison
MiniMax M2.5/M2.7 — H100 vs MI355X
Head-to-head AI inference benchmark comparison of H100 (NVIDIA Hopper) 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.
H100 posts 1,926 tok/s/chip for $0.17 per million tokens at 43 tok/s/user on MiniMax M2.5/M2.7; MI355X posts 4,697 tok/s/chip for $0.089. MI355X is 47% cheaper per token; MI355X delivers 144% more tok/s/chip.
Throughput at 66 tok/s/user on MiniMax M2.5/M2.7: H100 hits 1,269 tok/s/chip, MI355X hits 2,917. Costs per million tokens land at $0.26 and $0.14 respectively. MI355X is 44% cheaper per token; MI355X delivers 130% more tok/s/chip.
H100 / MI355X on MiniMax M2.5/M2.7 at 88 tok/s/user: 823 / 1,869 tok/s/chip, $0.39 / $0.22 per million tokens. MI355X is 44% cheaper per token; MI355X delivers 127% more tok/s/chip. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | H1001,926MI355X4,697 | H1001,269MI355X2,917 | H100823MI355X1,869 |
| Cost ($/M tok) | H100$0.17MI355X$0.089 | H100$0.26MI355X$0.14 | H100$0.39MI355X$0.22 |
| tok/s/MW | H1001,406,025MI355X2,247,388 | H100926,145MI355X1,395,931 | H100600,902MI355X894,417 |
| Concurrency | H100~41MI355X~43 | H100~18MI355X~10 | H100~9MI355X~5 |