Qwen 3.5 397B-A17B — GB300 NVL72 vs H100
Head-to-head AI inference benchmark comparison of GB300 NVL72 (NVIDIA Blackwell) and H100 (NVIDIA Hopper) 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.
At 63 tok/s/user on Qwen 3.5 397B-A17B, H100 delivers 517 tok/s/GPU at $0.73 per million tokens; GB300 NVL72 hasn't been benchmarked at this target.
H100 hits 220 tok/s/GPU for $1.66 per million tokens at 97 tok/s/user on Qwen 3.5 397B-A17B. No GB300 NVL72 data at this operating point.
H100: 86 tok/s/GPU, $4.06 per million tokens at 131 tok/s/user on Qwen 3.5 397B-A17B. GB300 NVL72 is unmeasured here. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | GB300 NVL72:—H100:517.2 | GB300 NVL72:—H100:220.0 | GB300 NVL72:—H100:86.2 |
| Cost ($/M tok) | GB300 NVL72:—H100:$0.726 | GB300 NVL72:—H100:$1.664 | GB300 NVL72:—H100:$4.057 |
| tok/s/MW | GB300 NVL72:—H100:298955 | GB300 NVL72:—H100:127176 | GB300 NVL72:—H100:49829 |
| Concurrency | GB300 NVL72:—H100:~39 | GB300 NVL72:—H100:~10 | GB300 NVL72:—H100:~3 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.