Kimi K2.5/K2.6/K2.7-Code 1T — Jalapeño vs MI325X
Head-to-head AI inference benchmark comparison of Jalapeño (OpenAI Jalapeño) and MI325X (AMD CDNA 3) on Kimi K2.5/K2.6/K2.7-Code 1T. 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.
Jalapeño hits 2143 tok/s/chip for $0.16 per million tokens at 219 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T. No MI325X data at this operating point.
Jalapeño: 724 tok/s/chip, $0.49 per million tokens at 377 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T. MI325X is unmeasured here.
At 536 tok/s/user on Kimi K2.5/K2.6/K2.7-Code 1T, Jalapeño delivers 682 tok/s/chip at $0.52 per million tokens; MI325X hasn't been benchmarked at this target. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | Jalapeño:2142.8MI325X:— | Jalapeño:724.5MI325X:— | Jalapeño:681.7MI325X:— |
| Cost ($/M tok) | Jalapeño:$0.165MI325X:— | Jalapeño:$0.487MI325X:— | Jalapeño:$0.517MI325X:— |
| tok/s/MW | Jalapeño:1904703MI325X:— | Jalapeño:643970MI325X:— | Jalapeño:605976MI325X:— |
| Concurrency | Jalapeño:~41MI325X:— | Jalapeño:~2MI325X:— | Jalapeño:~1MI325X:— |