Qwen 3.5 397B-A17B — GB200 NVL72 vs GB300 NVL72
Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and GB300 NVL72 (NVIDIA Blackwell) 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.
GB200 NVL72: 1239 tok/s/GPU, $0.51 per million tokens at 64 tok/s/user on Qwen 3.5 397B-A17B. GB300 NVL72 is unmeasured here.
At 101 tok/s/user on Qwen 3.5 397B-A17B, GB200 NVL72 delivers 464 tok/s/GPU at $1.30 per million tokens; GB300 NVL72 hasn't been benchmarked at this target.
GB200 NVL72 hits 206 tok/s/GPU for $2.98 per million tokens at 137 tok/s/user on Qwen 3.5 397B-A17B. No GB300 NVL72 data at this operating point. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | GB200 NVL72:1239.3GB300 NVL72:— | GB200 NVL72:463.7GB300 NVL72:— | GB200 NVL72:205.8GB300 NVL72:— |
| Cost ($/M tok) | GB200 NVL72:$0.506GB300 NVL72:— | GB200 NVL72:$1.297GB300 NVL72:— | GB200 NVL72:$2.983GB300 NVL72:— |
| tok/s/MW | GB200 NVL72:590129GB300 NVL72:— | GB200 NVL72:220809GB300 NVL72:— | GB200 NVL72:98013GB300 NVL72:— |
| Concurrency | GB200 NVL72:~113GB300 NVL72:— | GB200 NVL72:~20GB300 NVL72:— | GB200 NVL72:~7GB300 NVL72:— |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.