DeepSeek R1 — Jalapeño vs Vera Rubin NVL72
Head-to-head AI inference benchmark comparison of Jalapeño (OpenAI Jalapeño) and Vera Rubin NVL72 (NVIDIA Vera Rubin) 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 149 tok/s/user on DeepSeek R1: Jalapeño hits 9824 tok/s/chip, Vera Rubin NVL72 hits 0. Per-million costs land at $0.04 and $0.00 respectively. Comparable data is unavailable.
Jalapeño / Vera Rubin NVL72 on DeepSeek R1 at 233 tok/s/user: 3017 / 0 tok/s/chip, $0.12 / $0.00 per million tokens. Comparable data is unavailable.
Toward the upper edge of the 66–400 tok/s/user interactivity band, at 316 tok/s/user on DeepSeek R1: Jalapeño runs 1194 tok/s/chip at $0.30/M tokens, Vera Rubin NVL72 runs 0 at $0.00/M. Comparable data is unavailable. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | Jalapeño:9824.1Vera Rubin NVL72:0.0 | Jalapeño:3017.0Vera Rubin NVL72:0.0 | Jalapeño:1194.3Vera Rubin NVL72:0.0 |
| Cost ($/M tok) | Jalapeño:$0.036Vera Rubin NVL72:$0.000 | Jalapeño:$0.117Vera Rubin NVL72:$0.000 | Jalapeño:$0.295Vera Rubin NVL72:$0.000 |
| tok/s/MW | Jalapeño:8732528Vera Rubin NVL72:0 | Jalapeño:2681790Vera Rubin NVL72:0 | Jalapeño:1061601Vera Rubin NVL72:0 |
| Concurrency | Jalapeño:~449Vera Rubin NVL72:~400 | Jalapeño:~59Vera Rubin NVL72:~400 | Jalapeño:~14Vera Rubin NVL72:~400 |