Muse Spark Open 816B — MI355X vs TPU7x
Head-to-head AI inference benchmark comparison of MI355X (AMD CDNA 4) 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: MI355X hits 16515 tok/s/chip, TPU7x hits 17723. Per-million costs land at $0.03 and $0.02 respectively. TPU7x is 56% cheaper per token; TPU7x delivers 7% more tok/s/chip.
MI355X / TPU7x on Muse Spark Open 816B at 264 tok/s/user: 12288 / 14152 tok/s/chip, $0.03 / $0.02 per million tokens. TPU7x is 68% cheaper per token; TPU7x delivers 15% 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: MI355X runs 9533 tok/s/chip at $0.04/M tokens, TPU7x runs 9123 at $0.03/M. TPU7x is 39% cheaper per token; MI355X delivers 5% more tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | MI355X:16514.9TPU7x:17722.9 | MI355X:12288.3TPU7x:14151.8 | MI355X:9533.3TPU7x:9122.6 |
| Cost ($/M tok) | MI355X:$0.025TPU7x:$0.016 | MI355X:$0.034TPU7x:$0.020 | MI355X:$0.044TPU7x:$0.031 |
| tok/s/MW | MI355X:7901860TPU7x:14683445 | MI355X:5879562TPU7x:11724803 | MI355X:4561371TPU7x:7558056 |
| Concurrency | MI355X:~11TPU7x:~11 | MI355X:~11TPU7x:~9 | MI355X:~13TPU7x:~5 |