GLM 5/5.1 · GPU comparison

GLM 5/5.1 — GB200 NVL72 vs MI355X

Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) 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.

Throughput at 36 tok/s/user on GLM 5/5.1: GB200 NVL72 hits 10443 tok/s/GPU, MI355X hits 1218. Per-million costs land at $0.06 and $0.34 respectively. GB200 NVL72 is 474% cheaper per token; GB200 NVL72 delivers 757% more tok/s/GPU.

GB200 NVL72 / MI355X on GLM 5/5.1 at 43 tok/s/user: 10265 / 949 tok/s/GPU, $0.06 / $0.43 per million tokens. GB200 NVL72 is 627% cheaper per token; GB200 NVL72 delivers 982% more tok/s/GPU.

Toward the upper edge of the 30–56 tok/s/user interactivity band, at 50 tok/s/user on GLM 5/5.1: GB200 NVL72 runs 9984 tok/s/GPU at $0.06/M tokens, MI355X runs 670 at $0.63/M. GB200 NVL72 is 920% cheaper per token; GB200 NVL72 delivers 1390% more tok/s/GPU. (Numbers reflect the default 8k/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)
GB200 NVL72:10442.9MI355X:1218.0
GB200 NVL72:10265.2MI355X:948.6
GB200 NVL72:9983.9MI355X:670.1
Cost ($/M tok)
GB200 NVL72:$0.059MI355X:$0.338
GB200 NVL72:$0.060MI355X:$0.434
GB200 NVL72:$0.061MI355X:$0.627
tok/s/MW
GB200 NVL72:5584446MI355X:582775
GB200 NVL72:5489410MI355X:453886
GB200 NVL72:5338994MI355X:320643
Concurrency
GB200 NVL72:~2253MI355X:~8
GB200 NVL72:~1843MI355X:~8
GB200 NVL72:~1340MI355X:~7

Inference Performance

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

Vendor:
Aggregation:
Spec Decoding: