Qwen 3.5 397B-A17B · GPU comparison

Qwen 3.5 397B-A17B — B200 vs H100

Head-to-head AI inference benchmark comparison of B200 (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 66 tok/s/user interactivity on Qwen 3.5 397B-A17B, B200 delivers 3409 tok/s/GPU at $0.16 per million tokens; H100 delivers 422 tok/s/GPU at $0.87. B200 is 446% cheaper per token; B200 delivers 709% more tok/s/GPU at this point.

B200 posts 1731 tok/s/GPU for $0.32 per million tokens at 101 tok/s/user on Qwen 3.5 397B-A17B; H100 posts 308 tok/s/GPU for $1.16. B200 is 266% cheaper per token; B200 delivers 462% more tok/s/GPU.

Throughput at 136 tok/s/user on Qwen 3.5 397B-A17B: B200 hits 1096 tok/s/GPU, H100 hits 234. Per-million costs land at $0.49 and $1.55 respectively. B200 is 214% cheaper per token; B200 delivers 368% more tok/s/GPU. (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.)

View performance-per-dollar view →

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/gpu)
B200:3408.7H100:421.6
B200:1730.6H100:308.0
B200:1095.7H100:233.9
Cost ($/M tok)
B200:$0.160H100:$0.873
B200:$0.317H100:$1.159
B200:$0.494H100:$1.553
tok/s/MW
B200:1570810H100:243681
B200:797489H100:178055
B200:504913H100:135210
Concurrency
B200:~112H100:~26
B200:~38H100:~12
B200:~18H100:~7

Inference Performance

Inference performance metrics across different models, hardware configurations, and serving parameters.

Vendor:
Aggregation:
Spec Decoding: