Muse Spark Open 816B — B300 vs TPU7x
Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and TPU7x (Google Ironwood) 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 →
Throughput at 179 tok/s/user on Muse Spark Open 816B: B300 hits 27488 tok/s/chip, TPU7x hits 17723. Per-million costs land at $0.02 and $0.02 respectively. TPU7x is 41% cheaper per token; B300 delivers 55% more tok/s/chip.
B300 / TPU7x on Muse Spark Open 816B at 264 tok/s/user: 17624 / 14152 tok/s/chip, $0.04 / $0.02 per million tokens. TPU7x is 76% cheaper per token; B300 delivers 25% more tok/s/chip.
Toward the upper edge of the 95–432 tok/s/user interactivity band, at 348 tok/s/user on Muse Spark Open 816B: B300 runs 14970 tok/s/chip at $0.04/M tokens, TPU7x runs 9123 at $0.03/M. TPU7x is 34% cheaper per token; B300 delivers 64% more tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | B300:27488.2TPU7x:17722.9 | B300:17624.4TPU7x:14151.8 | B300:14970.1TPU7x:9122.6 |
| Cost ($/M tok) | B300:$0.023TPU7x:$0.016 | B300:$0.036TPU7x:$0.020 | B300:$0.042TPU7x:$0.031 |
| tok/s/MW | B300:14467489TPU7x:14683445 | B300:9275979TPU7x:11724803 | B300:7878974TPU7x:7558056 |
| Concurrency | B300:~18TPU7x:~11 | B300:~20TPU7x:~9 | B300:~17TPU7x:~5 |