DeepSeek V4.1 Flash 552B — MI300X vs MI325X
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 68 tok/s/user as the target on DeepSeek V4.1 Flash 552B, MI300X produces 11924 tok/s/chip ($0.02 per million tokens) and MI325X produces 16435 ($0.02). MI325X is 19% cheaper per token; MI325X delivers 38% more tok/s/chip.
At 113 tok/s/user interactivity on DeepSeek V4.1 Flash 552B, MI300X delivers 6980 tok/s/chip at $0.04 per million tokens; MI325X delivers 8049 tok/s/chip at $0.04. Cost per token is essentially tied; MI325X delivers 15% more tok/s/chip at this point.
MI300X posts 4040 tok/s/chip for $0.07 per million tokens at 159 tok/s/user on DeepSeek V4.1 Flash 552B; MI325X posts 4442 tok/s/chip for $0.07. MI300X is 5% cheaper per token; MI325X delivers 10% more tok/s/chip. (Numbers reflect the default agentic-traces · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | MI300X:11923.9MI325X:16434.6 | MI300X:6980.3MI325X:8048.9 | MI300X:4040.4MI325X:4441.9 |
| Cost ($/M tok) | MI300X:$0.022MI325X:$0.019 | MI300X:$0.038MI325X:$0.038 | MI300X:$0.065MI325X:$0.069 |
| tok/s/MW | MI300X:8578379MI325X:9724612 | MI300X:5021810MI325X:4762680 | MI300X:2906738MI325X:2628332 |
| Concurrency | MI300X:~9MI325X:~6 | MI300X:~5MI325X:~2 | MI300X:~1MI325X:~2 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.