gpt-oss 120B — MI300X vs MI325X
Head-to-head AI inference benchmark comparison of MI300X (AMD CDNA 3) 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.
Throughput at 50 tok/s/user on gpt-oss 120B: MI300X hits 3834 tok/s/GPU, MI325X hits 2738. Per-million costs land at $0.08 and $0.13 respectively. MI300X is 59% cheaper per token; MI300X delivers 40% more tok/s/GPU.
MI300X / MI325X on gpt-oss 120B at 71 tok/s/user: 3127 / 1953 tok/s/GPU, $0.10 / $0.18 per million tokens. MI300X is 80% cheaper per token; MI300X delivers 60% more tok/s/GPU.
Toward the upper edge of the 30–112 tok/s/user interactivity band, at 92 tok/s/user on gpt-oss 120B: MI300X runs 2051 tok/s/GPU at $0.15/M tokens, MI325X runs 983 at $0.35/M. MI300X is 137% cheaper per token; MI300X delivers 109% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | MI300X:3834.3MI325X:2738.2 | MI300X:3127.3MI325X:1952.6 | MI300X:2050.9MI325X:982.7 |
| Cost ($/M tok) | MI300X:$0.081MI325X:$0.129 | MI300X:$0.102MI325X:$0.183 | MI300X:$0.148MI325X:$0.351 |
| tok/s/MW | MI300X:2142060MI325X:1256065 | MI300X:1747115MI325X:895706 | MI300X:1145772MI325X:450777 |
| Concurrency | MI300X:~64MI325X:~64 | MI300X:~49MI325X:~62 | MI300X:~23MI325X:~22 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.