DeepSeek V4.1 Flash 552B β MI325X vs MI355X
Head-to-head AI inference benchmark comparison of MI325X (AMD CDNA 3) and MI355X (AMD CDNA 4) on DeepSeek V4.1 Flash 552B. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics β 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 β
MI325X / MI355X on DeepSeek V4.1 Flash 552B at 103 tok/s/user: 10087 / 155416 tok/s/chip, $0.03 / $0.00 per million tokens. MI355X is 1030% cheaper per token; MI355X delivers 1441% more tok/s/chip.
Around the middle of the 67β209 tok/s/user interactivity band, at 138 tok/s/user on DeepSeek V4.1 Flash 552B: MI325X runs 6588 tok/s/chip at $0.05/M tokens, MI355X runs 114437 at $0.00/M. MI355X is 1174% cheaper per token; MI355X delivers 1637% more tok/s/chip.
Setting 174 tok/s/user as the target on DeepSeek V4.1 Flash 552B, MI325X produces 4180 tok/s/chip ($0.07 per million tokens) and MI355X produces 110982 ($0.00). MI355X is 1847% cheaper per token; MI355X delivers 2555% more tok/s/chip. (Numbers reflect the default agentic-traces Β· fp4 selection for this URL β table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | MI325X:10086.7MI355X:155416.2 | MI325X:6588.3MI355X:114436.7 | MI325X:4179.6MI355X:110982.2 |
| Cost ($/M tok) | MI325X:$0.030MI355X:$0.003 | MI325X:$0.046MI355X:$0.004 | MI325X:$0.073MI355X:$0.004 |
| tok/s/MW | MI325X:5968461MI355X:74361825 | MI325X:3898375MI355X:54754379 | MI325X:2473119MI355X:53101540 |
| Concurrency | MI325X:~3MI355X:~52 | MI325X:~2MI355X:~32 | MI325X:~1MI355X:~32 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.