Qwen 3.5 397B-A17B · GPU comparison

Qwen 3.5 397B-A17B — H100 vs H200

Head-to-head AI inference benchmark comparison of H100 (NVIDIA Hopper) and H200 (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 64 tok/s/user interactivity on Qwen 3.5 397B-A17B, H100 delivers 433 tok/s/GPU at $0.85 per million tokens; H200 delivers 510 tok/s/GPU at $0.77. H200 is 10% cheaper per token; H200 delivers 18% more tok/s/GPU at this point.

H100 posts 311 tok/s/GPU for $1.15 per million tokens at 100 tok/s/user on Qwen 3.5 397B-A17B; H200 posts 366 tok/s/GPU for $1.07. H200 is 8% cheaper per token; H200 delivers 18% more tok/s/GPU.

Throughput at 135 tok/s/user on Qwen 3.5 397B-A17B: H100 hits 236 tok/s/GPU, H200 hits 302. Per-million costs land at $1.54 and $1.27 respectively. H200 is 21% cheaper per token; H200 delivers 28% 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)
H100:433.3H200:510.5
H100:310.5H200:366.2
H100:236.1H200:302.5
Cost ($/M tok)
H100:$0.848H200:$0.767
H100:$1.151H200:$1.065
H100:$1.536H200:$1.273
tok/s/MW
H100:250452H200:295059
H100:179506H200:211671
H100:136470H200:174833
Concurrency
H100:~28H200:~32
H100:~13H200:~15
H100:~7H200:~9

Inference Performance

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

Vendor:
Aggregation:
Spec Decoding: