Qwen 3.5 397B-A17B · GPU comparison

Qwen 3.5 397B-A17B — H100 vs MI300X

Head-to-head AI inference benchmark comparison of H100 (NVIDIA Hopper) and MI300X (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.

H100 posts 1033 tok/s/GPU for $0.35 per million tokens at 43 tok/s/user on Qwen 3.5 397B-A17B; MI300X posts 346 tok/s/GPU for $0.89. H100 is 154% cheaper per token; H100 delivers 199% more tok/s/GPU.

Throughput at 53 tok/s/user on Qwen 3.5 397B-A17B: H100 hits 776 tok/s/GPU, MI300X hits 190. Per-million costs land at $0.47 and $1.63 respectively. H100 is 249% cheaper per token; H100 delivers 309% more tok/s/GPU.

H100 / MI300X on Qwen 3.5 397B-A17B at 62 tok/s/user: 447 / 123 tok/s/GPU, $0.82 / $2.52 per million tokens. H100 is 207% cheaper per token; H100 delivers 264% 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)
H100:1032.9MI300X:345.8
H100:775.8MI300X:189.5
H100:446.6MI300X:122.7
Cost ($/M tok)
H100:$0.351MI300X:$0.893
H100:$0.468MI300X:$1.633
H100:$0.818MI300X:$2.517
tok/s/MW
H100:597043MI300X:193162
H100:448438MI300X:105886
H100:258172MI300X:68573
Concurrency
H100:~106MI300X:~34
H100:~67MI300X:~15
H100:~29MI300X:~8

Inference Performance

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

Vendor:
Aggregation:
Spec Decoding: