MiniMax M2.5/M2.7 — H100 vs MI325X
Head-to-head AI inference benchmark comparison of H100 (NVIDIA Hopper) 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.
Near the low end of the 21–99 tok/s/user interactivity band, at 41 tok/s/user on MiniMax M2.5/M2.7: H100 runs 1998 tok/s/chip at $0.16/M tokens, MI325X runs 2371 at $0.13/M. MI325X is 26% cheaper per token; MI325X delivers 19% more tok/s/chip.
Setting 60 tok/s/user as the target on MiniMax M2.5/M2.7, H100 produces 1412 tok/s/chip ($0.23 per million tokens) and MI325X produces 1661 ($0.18). MI325X is 25% cheaper per token; MI325X delivers 18% more tok/s/chip.
At 80 tok/s/user interactivity on MiniMax M2.5/M2.7, H100 delivers 969 tok/s/chip at $0.34 per million tokens; MI325X delivers 943 tok/s/chip at $0.32. MI325X is 3% cheaper per token; H100 delivers 3% more tok/s/chip at this point. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | H100:1998.4MI325X:2370.7 | H100:1412.3MI325X:1660.9 | H100:969.2MI325X:942.7 |
| Cost ($/M tok) | H100:$0.163MI325X:$0.129 | H100:$0.230MI325X:$0.184 | H100:$0.335MI325X:$0.324 |
| tok/s/MW | H100:1458672MI325X:1402785 | H100:1030898MI325X:982768 | H100:707434MI325X:557830 |
| Concurrency | H100:~44MI325X:~13 | H100:~22MI325X:~6 | H100:~11MI325X:~6 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
Total Tokens per $1 USD (Owning - Hyperscaler) vs. Interactivity
MiniMax M2.5/2.7 230B • FP4 • 8K / 1K • Source: SemiAnalysis InferenceX™
TCO $/chip/hr: H100: 1.17H200: 1.22B200: 1.73B300: 2.26GB200: 1.86GB300: 2.31MI300X: 0.95MI325X: 1.1MI355X: 1.5RTX6000PRO: 0.68
Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate cost per million tokens per decode chip or per prefill chip, rather than per total chip count. This makes direct token cost comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate input throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct input throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate output throughput per decode chip or per prefill chip, rather than per total chip count. This makes direct output throughput comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate power per decode chip or per prefill chip, rather than per total chip count. This makes direct power comparison with aggregated configs not an apples-to-apples comparison.
Note: Disaggregated inference configurations (e.g., MoRI SGLang, Dynamo TRTLLM) calculate Joules per decode chip or per prefill chip, rather than per total chip count. This makes direct Joules per token comparison with aggregated configs not an apples-to-apples comparison.
No data available
Please change the model, sequence, precision, date range or chip selection.
Shift+Scroll to zoom • Drag to pan • Double-click to reset • Click a point to pin tooltip