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 308 tok/s/GPU for $1.20 per million tokens at 52 tok/s/user on Qwen 3.5 397B-A17B; MI300X posts 201 tok/s/GPU for $1.55. H100 is 29% cheaper per token; H100 delivers 53% more tok/s/GPU.
Throughput at 58 tok/s/user on Qwen 3.5 397B-A17B: H100 hits 270 tok/s/GPU, MI300X hits 147. Per-million costs land at $1.35 and $2.04 respectively. H100 is 51% cheaper per token; H100 delivers 84% more tok/s/GPU.
H100 / MI300X on Qwen 3.5 397B-A17B at 65 tok/s/user: 235 / 104 tok/s/GPU, $1.53 / $3.05 per million tokens. H100 is 100% cheaper per token; H100 delivers 126% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | H100:307.6MI300X:201.4 | H100:270.4MI300X:147.3 | H100:234.9MI300X:103.9 |
| Cost ($/M tok) | H100:$1.198MI300X:$1.547 | H100:$1.352MI300X:$2.044 | H100:$1.527MI300X:$3.054 |
| tok/s/MW | H100:177792MI300X:112516 | H100:156311MI300X:82288 | H100:135793MI300X:58024 |
| Concurrency | H100:~25MI300X:~16 | H100:~19MI300X:~11 | H100:~15MI300X:~7 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.