gpt-oss 120B · GPU comparison

gpt-oss 120B — MI325X vs MI355X

Head-to-head AI inference benchmark comparison of MI325X (AMD CDNA 3) and MI355X (AMD CDNA 4) on gpt-oss 120B. 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.

At 75 tok/s/user interactivity on gpt-oss 120B, MI325X delivers 1687 tok/s/GPU at $0.22 per million tokens; MI355X delivers 16349 tok/s/GPU at $0.03. MI355X is 750% cheaper per token; MI355X delivers 869% more tok/s/GPU at this point.

MI325X posts 1060 tok/s/GPU for $0.32 per million tokens at 88 tok/s/user on gpt-oss 120B; MI355X posts 13114 tok/s/GPU for $0.03. MI355X is 930% cheaper per token; MI355X delivers 1137% more tok/s/GPU.

Throughput at 100 tok/s/user on gpt-oss 120B: MI325X hits 805 tok/s/GPU, MI355X hits 10663. Per-million costs land at $0.44 and $0.04 respectively. MI355X is 1047% cheaper per token; MI355X delivers 1224% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)

View performance-per-dollar view →

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/gpu)
MI325X:1686.7MI355X:16349.2
MI325X:1060.0MI355X:13114.0
MI325X:805.4MI355X:10662.6
Cost ($/M tok)
MI325X:$0.216MI355X:$0.025
MI325X:$0.324MI355X:$0.031
MI325X:$0.443MI355X:$0.039
tok/s/MW
MI325X:773696MI355X:6169505
MI325X:486224MI355X:4948695
MI325X:369456MI355X:4023613
Concurrency
MI325X:~52MI355X:~114
MI325X:~25MI355X:~78
MI325X:~17MI355X:~54

Inference Performance

Inference performance metrics across different models, hardware configurations, and serving parameters.