DeepSeek R1 — Jalapeño vs MI300X
Head-to-head AI inference benchmark comparison of Jalapeño (OpenAI Jalapeño) and MI300X (AMD CDNA 3) on DeepSeek R1. 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 3548 tok/s/chip for $0.10 per million tokens at 225 tok/s/user on DeepSeek R1. No MI300X data at this operating point.
Jalapeño: 736 tok/s/chip, $0.48 per million tokens at 384 tok/s/user on DeepSeek R1. MI300X is unmeasured here.
At 544 tok/s/user on DeepSeek R1, Jalapeño delivers 654 tok/s/chip at $0.54 per million tokens; MI300X hasn't been benchmarked at this target. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | Jalapeño:3548.2MI300X:— | Jalapeño:735.7MI300X:— | Jalapeño:654.2MI300X:— |
| Cost ($/M tok) | Jalapeño:$0.099MI300X:— | Jalapeño:$0.480MI300X:— | Jalapeño:$0.539MI300X:— |
| tok/s/MW | Jalapeño:3153917MI300X:— | Jalapeño:653973MI300X:— | Jalapeño:581488MI300X:— |
| Concurrency | Jalapeño:~75MI300X:— | Jalapeño:~3MI300X:— | Jalapeño:~1MI300X:— |