MiniMax M2.5/M2.7 — GB300 NVL72 vs MI355X
Head-to-head AI inference benchmark comparison of GB300 NVL72 (NVIDIA Blackwell) and MI355X (AMD CDNA 4) on MiniMax M2.5/M2.7. 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 posts 5457 tok/s/GPU for $0.14 per million tokens at 47 tok/s/user on MiniMax M2.5/M2.7; MI355X posts 3554 tok/s/GPU for $0.12. MI355X is 17% cheaper per token; GB300 NVL72 delivers 54% more tok/s/GPU.
Throughput at 71 tok/s/user on MiniMax M2.5/M2.7: GB300 NVL72 hits 2467 tok/s/GPU, MI355X hits 1074. Per-million costs land at $0.31 and $0.38 respectively. GB300 NVL72 is 22% cheaper per token; GB300 NVL72 delivers 130% more tok/s/GPU.
GB300 NVL72 / MI355X on MiniMax M2.5/M2.7 at 95 tok/s/user: 924 / 541 tok/s/GPU, $0.82 / $0.73 per million tokens. MI355X is 13% cheaper per token; GB300 NVL72 delivers 71% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | GB300 NVL72:5457.1MI355X:3553.8 | GB300 NVL72:2466.7MI355X:1074.1 | GB300 NVL72:924.1MI355X:540.6 |
| Cost ($/M tok) | GB300 NVL72:$0.136MI355X:$0.117 | GB300 NVL72:$0.313MI355X:$0.383 | GB300 NVL72:$0.823MI355X:$0.732 |
| tok/s/MW | GB300 NVL72:2598642MI355X:1341039 | GB300 NVL72:1174626MI355X:405332 | GB300 NVL72:440064MI355X:204005 |
| Concurrency | GB300 NVL72:~540MI355X:~256 | GB300 NVL72:~128MI355X:~32 | GB300 NVL72:~32MI355X:~6 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.