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 90% 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. Per-million costs land at $0.26 and $0.14 respectively. MI355X is 79% 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 77% 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.)

View performance per dollar →

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)
H1001,926.3MI355X4,697.0
H1001,268.8MI355X2,917.5
H100823.2MI355X1,869.3
Cost ($/M tok)
H100$0.169MI355X$0.089
H100$0.256MI355X$0.143
H100$0.395MI355X$0.223
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