GLM 5/5.1 · GPU comparison

GLM 5/5.1 — GB300 NVL72 vs MI325X

Head-to-head AI inference benchmark comparison of GB300 NVL72 (NVIDIA Blackwell) and MI325X (AMD CDNA 3) on GLM 5/5.1. 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.

GB300 NVL72: 6679 tok/s/GPU, $0.11 per million tokens at 69 tok/s/user on GLM 5/5.1. MI325X is unmeasured here.

At 121 tok/s/user on GLM 5/5.1, GB300 NVL72 delivers 811 tok/s/GPU at $0.91 per million tokens; MI325X hasn't been benchmarked at this target.

GB300 NVL72 hits 151 tok/s/GPU for $4.87 per million tokens at 173 tok/s/user on GLM 5/5.1. No MI325X data at this operating point. (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)
GB300 NVL72:6679.2MI325X:
GB300 NVL72:810.6MI325X:
GB300 NVL72:151.3MI325X:
Cost ($/M tok)
GB300 NVL72:$0.110MI325X:
GB300 NVL72:$0.910MI325X:
GB300 NVL72:$4.870MI325X:
tok/s/MW
GB300 NVL72:3180562MI325X:
GB300 NVL72:385983MI325X:
GB300 NVL72:72026MI325X:
Concurrency
GB300 NVL72:~1221MI325X:
GB300 NVL72:~166MI325X:
GB300 NVL72:~23MI325X:

Inference Performance

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

Vendor:
Aggregation:
Spec Decoding: