Qwen 3.5 397B-A17B — GB200 NVL72 vs MI325X
Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and MI325X (AMD CDNA 3) 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 →
At 15 tok/s/user on Qwen 3.5 397B-A17B, MI325X delivers 17400 tok/s/chip at $0.02 per million tokens; GB200 NVL72 hasn't been benchmarked at this target.
MI325X hits 11265 tok/s/chip for $0.03 per million tokens at 30 tok/s/user on Qwen 3.5 397B-A17B. No GB200 NVL72 data at this operating point.
MI325X: 8282 tok/s/chip, $0.04 per million tokens at 44 tok/s/user on Qwen 3.5 397B-A17B. GB200 NVL72 is unmeasured here. (Numbers reflect the default agentic-traces · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | GB200 NVL72:—MI325X:17399.8 | GB200 NVL72:—MI325X:11265.0 | GB200 NVL72:—MI325X:8281.9 |
| Cost ($/M tok) | GB200 NVL72:—MI325X:$0.018 | GB200 NVL72:—MI325X:$0.027 | GB200 NVL72:—MI325X:$0.037 |
| tok/s/MW | GB200 NVL72:—MI325X:10295725 | GB200 NVL72:—MI325X:6665686 | GB200 NVL72:—MI325X:4900558 |
| Concurrency | GB200 NVL72:—MI325X:~32 | GB200 NVL72:—MI325X:~21 | GB200 NVL72:—MI325X:~10 |