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 β same interactions as the main inference chart.
At 30 tok/s/user interactivity on MiniMax M2.5/M2.7, MI300X delivers 1570 tok/s/chip at $0.17 per million tokens; MI325X delivers 2916 tok/s/chip at $0.10. MI325X is 60% cheaper per token; MI325X delivers 86% more tok/s/chip at this point.
MI300X posts 1412 tok/s/chip for $0.19 per million tokens at 48 tok/s/user on MiniMax M2.5/M2.7; MI325X posts 2106 tok/s/chip for $0.15. MI325X is 29% cheaper per token; MI325X delivers 49% more tok/s/chip.
Throughput at 66 tok/s/user on MiniMax M2.5/M2.7: MI300X hits 1086 tok/s/chip, MI325X hits 1433. Per-million costs land at $0.24 and $0.21 respectively. MI325X is 14% cheaper per token; MI325X delivers 32% more tok/s/chip. (Numbers reflect the default 8k/1k Β· fp8 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | MI300X:1570.4MI325X:2915.6 | MI300X:1412.0MI325X:2106.1 | MI300X:1085.6MI325X:1432.8 |
| Cost ($/M tok) | MI300X:$0.168MI325X:$0.105 | MI300X:$0.187MI325X:$0.145 | MI300X:$0.243MI325X:$0.213 |
| tok/s/MW | MI300X:1129783MI325X:1725192 | MI300X:1015827MI325X:1246204 | MI300X:781024MI325X:847801 |
| Concurrency | MI300X:~20MI325X:~22 | MI300X:~7MI325X:~10 | MI300X:~4MI325X:~5 |
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
TCO $/chip/hr:
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 measurements to plot for this selection. Review the benchmark controls above or adjust quick filters.
Shift+Scroll to zoom β’ Drag to pan β’ Double-click to reset β’ Click a point to pin tooltip
MiniMax M2.5/2.7 230B 8K / 1K Total Tokens per $1 TCO vs. Interactivity