DeepSeek R1 · Chip comparison

DeepSeek R1 — MI300X vs MI355X

Head-to-head AI inference benchmark comparison of MI300X (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.

Near the low end of the 13–54 tok/s/user interactivity band, at 23 tok/s/user on DeepSeek R1: MI300X runs 706 tok/s/chip at $0.37 per million tokens, MI355X runs 3,489 at $0.12. MI355X is 68% cheaper per token; MI355X delivers 4.9× the tok/s/chip.

Setting 33 tok/s/user as the target on DeepSeek R1, MI300X produces 592 tok/s/chip ($0.45 per million tokens) and MI355X produces 2,873 ($0.15). MI355X is 67% cheaper per token; MI355X delivers 4.8× the tok/s/chip.

At 44 tok/s/user interactivity on DeepSeek R1, MI300X delivers 407 tok/s/chip at $0.65 per million tokens; MI355X delivers 2,319 tok/s/chip at $0.18. MI355X is 72% cheaper per token; MI355X delivers 5.7× the tok/s/chip at this point. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)

View performance per dollar →

Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.

Metric
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Throughput (tok/s/chip)
MI300X706MI355X3,489
MI300X592MI355X2,873
MI300X407MI355X2,319
Cost ($/M tok)
MI300X$0.37MI355X$0.12
MI300X$0.45MI355X$0.15
MI300X$0.65MI355X$0.18
tok/s/MW
MI300X508,108MI355X1,669,564
MI300X426,187MI355X1,374,549
MI300X293,040MI355X1,109,710
Concurrency
MI300X~28MI355X~2,048
MI300X~17MI355X~623
MI300X~9MI355X~44