gpt-oss 120B — H200 vs MI300X
Head-to-head AI inference benchmark comparison of H200 (NVIDIA Hopper) and MI300X (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.
At 92 tok/s/user interactivity on gpt-oss 120B, H200 delivers 3637 tok/s/GPU at $0.11 per million tokens; MI300X delivers 2051 tok/s/GPU at $0.15. H200 is 38% cheaper per token; H200 delivers 77% more tok/s/GPU at this point.
H200 posts 2053 tok/s/GPU for $0.19 per million tokens at 144 tok/s/user on gpt-oss 120B; MI300X posts 957 tok/s/GPU for $0.32. H200 is 68% cheaper per token; H200 delivers 115% more tok/s/GPU.
Throughput at 197 tok/s/user on gpt-oss 120B: H200 hits 1050 tok/s/GPU, MI300X hits 355. Per-million costs land at $0.37 and $0.87 respectively. H200 is 137% cheaper per token; H200 delivers 196% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | H200:3636.7MI300X:2050.9 | H200:2053.2MI300X:956.8 | H200:1050.5MI300X:355.0 |
| Cost ($/M tok) | H200:$0.108MI300X:$0.148 | H200:$0.191MI300X:$0.320 | H200:$0.368MI300X:$0.872 |
| tok/s/MW | H200:2102136MI300X:1145772 | H200:1186798MI300X:534550 | H200:607224MI300X:198311 |
| Concurrency | H200:~64MI300X:~23 | H200:~63MI300X:~7 | H200:~17MI300X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.