gpt-oss 120B — H200 vs MI325X
Head-to-head AI inference benchmark comparison of H200 (NVIDIA Hopper) and MI325X (AMD CDNA 3) on gpt-oss 120B. 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.
H200 posts 4718 tok/s/GPU for $0.08 per million tokens at 58 tok/s/user on gpt-oss 120B; MI325X posts 2565 tok/s/GPU for $0.14. H200 is 69% cheaper per token; H200 delivers 84% more tok/s/GPU.
Throughput at 77 tok/s/user on gpt-oss 120B: H200 hits 4168 tok/s/GPU, MI325X hits 1472. Per-million costs land at $0.09 and $0.25 respectively. H200 is 164% cheaper per token; H200 delivers 183% more tok/s/GPU.
H200 / MI325X on gpt-oss 120B at 95 tok/s/user: 3529 / 991 tok/s/GPU, $0.11 / $0.36 per million tokens. H200 is 225% cheaper per token; H200 delivers 256% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | H200:4717.8MI325X:2565.4 | H200:4168.1MI325X:1471.9 | H200:3529.5MI325X:991.0 |
| Cost ($/M tok) | H200:$0.083MI325X:$0.139 | H200:$0.094MI325X:$0.249 | H200:$0.111MI325X:$0.360 |
| tok/s/MW | H200:2727033MI325X:1176771 | H200:2409279MI325X:675165 | H200:2040148MI325X:454581 |
| Concurrency | H200:~64MI325X:~64 | H200:~64MI325X:~29 | H200:~64MI325X:~23 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.