Qwen 3.5 397B-A17B · Chip comparison
Qwen 3.5 397B-A17B — RTX PRO 6000 vs TPU7x
Head-to-head AI inference benchmark comparison of RTX PRO 6000 (NVIDIA Blackwell) and TPU7x (Google Ironwood) on Qwen 3.5 397B-A17B. 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 →
TPU7x: 45,533 tok/s/chip, $0.006 per million tokens at 327 tok/s/user on Qwen 3.5 397B-A17B. RTX PRO 6000 is unmeasured here.
At 573 tok/s/user on Qwen 3.5 397B-A17B, TPU7x delivers 37,264 tok/s/chip at $0.008 per million tokens; RTX PRO 6000 hasn't been benchmarked at this target.
TPU7x hits 28,384 tok/s/chip for $0.010 per million tokens at 818 tok/s/user on Qwen 3.5 397B-A17B. No RTX PRO 6000 data at this operating point. (Numbers reflect the default agentic-traces · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | RTX PRO 6000—TPU7x45,533 | RTX PRO 6000—TPU7x37,264 | RTX PRO 6000—TPU7x28,384 |
| Cost ($/M tok) | RTX PRO 6000—TPU7x$0.006 | RTX PRO 6000—TPU7x$0.008 | RTX PRO 6000—TPU7x$0.010 |
| tok/s/MW | RTX PRO 6000—TPU7x37,724,292 | RTX PRO 6000—TPU7x30,873,240 | RTX PRO 6000—TPU7x23,516,277 |
| Concurrency | RTX PRO 6000—TPU7x~224 | RTX PRO 6000—TPU7x~212 | RTX PRO 6000—TPU7x~169 |