Head-to-head AI inference benchmark comparison of MI300X (AMD CDNA 3) and MI325X (AMD CDNA 3) on DeepSeek V4.1 Flash 552B. 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.
AgentX replays real coding-agent sessions rather than fixed-length prompts, so context grows turn over turn and most of each request is served from cache instead of being recomputed. That turns the comparison into a systems question: KV transfer between nodes, prefix-aware routing, and cache capacity all move the curve alongside raw chip throughput. Fixed-sequence workloads stay the clean baseline for kernel and silicon performance, so the two scenarios answer different questions about the same hardware. Learn more about AgentX →
Setting 67 tok/s/user as the target on DeepSeek V4.1 Flash 552B, MI300X produces 5805 tok/s/chip ($0.05 per million tokens) and MI325X produces 7411 ($0.04). MI325X is 10% cheaper per token; MI325X delivers 28% more tok/s/chip.
At 108 tok/s/user interactivity on DeepSeek V4.1 Flash 552B, MI300X delivers 3928 tok/s/chip at $0.07 per million tokens; MI325X delivers 5098 tok/s/chip at $0.06. MI325X is 12% cheaper per token; MI325X delivers 30% more tok/s/chip at this point.
MI300X posts 2118 tok/s/chip for $0.12 per million tokens at 149 tok/s/user on DeepSeek V4.1 Flash 552B; MI325X posts 3849 tok/s/chip for $0.08. MI325X is 57% cheaper per token; MI325X delivers 82% more tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | MI300X:5805.1MI325X:7411.1 | MI300X:3927.5MI325X:5098.5 | MI300X:2118.4MI325X:3849.2 |
| Cost ($/M tok) | MI300X:$0.045MI325X:$0.041 | MI300X:$0.067MI325X:$0.060 | MI300X:$0.125MI325X:$0.079 |
| tok/s/MW | MI300X:4176322MI325X:4385275 | MI300X:2825572MI325X:3016836 | MI300X:1523994MI325X:2277639 |
| Concurrency | MI300X:~9MI325X:~11 | MI300X:~5MI325X:~7 | MI300X:~2MI325X:~5 |
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
No measurements to plot for this selection. Review the benchmark controls above or adjust quick filters.
