Muse Spark Open 816B — TPU7x vs Vera Rubin NVL72
Head-to-head AI inference benchmark comparison of TPU7x (Google Ironwood) and Vera Rubin NVL72 (NVIDIA Vera Rubin) on Muse Spark Open 816B. 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.
AgentX replays real coding-agent sessions rather than fixed-length prompts, so context grows turn over turn and most of each request is served from cache instead of being recomputed. That turns the comparison into a systems question: KV transfer between nodes, prefix-aware routing, and cache capacity all move the curve alongside raw chip throughput. Fixed-sequence workloads stay the clean baseline for kernel and silicon performance, so the two scenarios answer different questions about the same hardware. Learn more about AgentX →
Near the low end of the 107–432 tok/s/user interactivity band, at 188 tok/s/user on Muse Spark Open 816B: TPU7x runs 17162 tok/s/chip at $0.02/M tokens, Vera Rubin NVL72 runs 87182 at $0.01/M. Vera Rubin NVL72 is 45% cheaper per token; Vera Rubin NVL72 delivers 408% more tok/s/chip.
Setting 270 tok/s/user as the target on Muse Spark Open 816B, TPU7x produces 13731 tok/s/chip ($0.02 per million tokens) and Vera Rubin NVL72 produces 62325 ($0.02). Vera Rubin NVL72 is 30% cheaper per token; Vera Rubin NVL72 delivers 354% more tok/s/chip.
At 351 tok/s/user interactivity on Muse Spark Open 816B, TPU7x delivers 8993 tok/s/chip at $0.03 per million tokens; Vera Rubin NVL72 delivers 49886 tok/s/chip at $0.02. Vera Rubin NVL72 is 58% cheaper per token; Vera Rubin NVL72 delivers 455% more tok/s/chip at this point. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | TPU7x:17162.4Vera Rubin NVL72:87181.7 | TPU7x:13731.5Vera Rubin NVL72:62325.3 | TPU7x:8993.4Vera Rubin NVL72:49885.8 |
| Cost ($/M tok) | TPU7x:$0.017Vera Rubin NVL72:$0.012 | TPU7x:$0.021Vera Rubin NVL72:$0.016 | TPU7x:$0.032Vera Rubin NVL72:$0.020 |
| tok/s/MW | TPU7x:14219073Vera Rubin NVL72:26418704 | TPU7x:11376540Vera Rubin NVL72:18886449 | TPU7x:7451065Vera Rubin NVL72:15116901 |
| Concurrency | TPU7x:~11Vera Rubin NVL72:~49 | TPU7x:~8Vera Rubin NVL72:~33 | TPU7x:~5Vera Rubin NVL72:~25 |