DeepSeek R1 — Jalapeño vs MI355X
Head-to-head AI inference benchmark comparison of Jalapeño (OpenAI Jalapeño) and MI355X (AMD CDNA 4) 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.
Throughput at 137 tok/s/user on DeepSeek R1: Jalapeño hits 10472 tok/s/chip, MI355X hits 3376. Per-million costs land at $0.03 and $0.12 respectively. Jalapeño is 266% cheaper per token; Jalapeño delivers 210% more tok/s/chip.
Jalapeño / MI355X on DeepSeek R1 at 208 tok/s/user: 5009 / 908 tok/s/chip, $0.07 / $0.46 per million tokens. Jalapeño is 552% cheaper per token; Jalapeño delivers 452% more tok/s/chip.
Toward the upper edge of the 66–350 tok/s/user interactivity band, at 279 tok/s/user on DeepSeek R1: Jalapeño runs 1681 tok/s/chip at $0.21/M tokens, MI355X runs 515 at $0.81/M. Jalapeño is 285% cheaper per token; Jalapeño delivers 226% more tok/s/chip. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | Jalapeño:10471.5MI355X:3376.4 | Jalapeño:5009.1MI355X:907.9 | Jalapeño:1681.3MI355X:515.3 |
| Cost ($/M tok) | Jalapeño:$0.034MI355X:$0.123 | Jalapeño:$0.070MI355X:$0.459 | Jalapeño:$0.210MI355X:$0.809 |
| tok/s/MW | Jalapeño:9308020MI355X:1615500 | Jalapeño:4452578MI355X:434386 | Jalapeño:1494490MI355X:246569 |
| Concurrency | Jalapeño:~555MI355X:~64 | Jalapeño:~122MI355X:~6 | Jalapeño:~26MI355X:~5 |