DeepSeek R1 — MI325X vs MI355X
Head-to-head AI inference benchmark comparison of MI325X (AMD CDNA 3) and MI355X (AMD CDNA 4) 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.
Setting 39 tok/s/user as the target on DeepSeek R1, MI325X produces 341 tok/s/GPU ($1.03 per million tokens) and MI355X produces 1719 ($0.24). MI355X is 330% cheaper per token; MI355X delivers 404% more tok/s/GPU.
At 50 tok/s/user interactivity on DeepSeek R1, MI325X delivers 225 tok/s/GPU at $1.57 per million tokens; MI355X delivers 1278 tok/s/GPU at $0.32. MI355X is 389% cheaper per token; MI355X delivers 467% more tok/s/GPU at this point.
MI325X posts 132 tok/s/GPU for $2.67 per million tokens at 60 tok/s/user on DeepSeek R1; MI355X posts 634 tok/s/GPU for $0.66. MI355X is 307% cheaper per token; MI355X delivers 380% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | MI325X:341.4MI355X:1719.1 | MI325X:225.5MI355X:1278.5 | MI325X:132.2MI355X:634.3 |
| Cost ($/M tok) | MI325X:$1.027MI355X:$0.239 | MI325X:$1.566MI355X:$0.320 | MI325X:$2.672MI355X:$0.656 |
| tok/s/MW | MI325X:156612MI355X:648714 | MI325X:103433MI355X:482434 | MI325X:60648MI355X:239341 |
| Concurrency | MI325X:~39MI355X:~729 | MI325X:~19MI355X:~363 | MI325X:~9MI355X:~157 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.