DeepSeek R1 — MI300X vs MI325X
Head-to-head AI inference benchmark comparison of MI300X (AMD CDNA 3) and MI325X (AMD CDNA 3) on DeepSeek R1. 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.
MI300X posts 244 tok/s/GPU for $1.27 per million tokens at 39 tok/s/user on DeepSeek R1; MI325X posts 341 tok/s/GPU for $1.03. MI325X is 24% cheaper per token; MI325X delivers 40% more tok/s/GPU.
Throughput at 49 tok/s/user on DeepSeek R1: MI300X hits 172 tok/s/GPU, MI325X hits 237. Per-million costs land at $1.81 and $1.49 respectively. MI325X is 21% cheaper per token; MI325X delivers 37% more tok/s/GPU.
MI300X / MI325X on DeepSeek R1 at 59 tok/s/user: 108 / 140 tok/s/GPU, $2.89 / $2.52 per million tokens. MI325X is 15% cheaper per token; MI325X delivers 30% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | MI300X:243.5MI325X:341.4 | MI300X:172.5MI325X:236.6 | MI300X:107.7MI325X:140.3 |
| Cost ($/M tok) | MI300X:$1.271MI325X:$1.027 | MI300X:$1.813MI325X:$1.493 | MI300X:$2.892MI325X:$2.517 |
| tok/s/MW | MI300X:136061MI325X:156612 | MI300X:96360MI325X:108535 | MI300X:60185MI325X:64361 |
| Concurrency | MI300X:~26MI325X:~39 | MI300X:~15MI325X:~20 | MI300X:~8MI325X:~10 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.