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 37 tok/s/user on GLM 5/5.1: GB200 NVL72 hits 2074 tok/s/GPU, MI355X hits 1173. Per-million costs land at $0.31 and $0.35 respectively. GB200 NVL72 is 12% cheaper per token; GB200 NVL72 delivers 77% more tok/s/GPU.
GB200 NVL72 / MI355X on GLM 5/5.1 at 45 tok/s/user: 635 / 1022 tok/s/GPU, $0.96 / $0.40 per million tokens. MI355X is 142% cheaper per token; MI355X delivers 61% more tok/s/GPU.
Toward the upper edge of the 29–62 tok/s/user interactivity band, at 54 tok/s/user on GLM 5/5.1: GB200 NVL72 runs 158 tok/s/GPU at $4.50/M tokens, MI355X runs 920 at $0.45/M. MI355X is 907% cheaper per token; MI355X delivers 483% more tok/s/GPU. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | GB200 NVL72:2073.9MI355X:1173.0 | GB200 NVL72:635.4MI355X:1022.3 | GB200 NVL72:157.8MI355X:920.0 |
| Cost ($/M tok) | GB200 NVL72:$0.311MI355X:$0.349 | GB200 NVL72:$0.957MI355X:$0.396 | GB200 NVL72:$4.499MI355X:$0.447 |
| tok/s/MW | GB200 NVL72:987580MI355X:442655 | GB200 NVL72:302553MI355X:385761 | GB200 NVL72:75151MI355X:347177 |
| Concurrency | GB200 NVL72:~931MI355X:~15 | GB200 NVL72:~150MI355X:~11 | GB200 NVL72:~27MI355X:~8 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.