MiniMax M2.5/M2.7 — GB300 NVL72 vs MI300X
Head-to-head AI inference benchmark comparison of GB300 NVL72 (NVIDIA Blackwell) and MI300X (AMD CDNA 3) 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.
Setting 44 tok/s/user as the target on MiniMax M2.5/M2.7, GB300 NVL72 produces 6594 tok/s/GPU ($0.11 per million tokens) and MI300X produces 1249 ($0.25). GB300 NVL72 is 119% cheaper per token; GB300 NVL72 delivers 428% more tok/s/GPU.
At 61 tok/s/user interactivity on MiniMax M2.5/M2.7, GB300 NVL72 delivers 3816 tok/s/GPU at $0.20 per million tokens; MI300X delivers 779 tok/s/GPU at $0.40. GB300 NVL72 is 104% cheaper per token; GB300 NVL72 delivers 390% more tok/s/GPU at this point.
GB300 NVL72 posts 1610 tok/s/GPU for $0.48 per million tokens at 78 tok/s/user on MiniMax M2.5/M2.7; MI300X posts 412 tok/s/GPU for $0.75. GB300 NVL72 is 56% cheaper per token; GB300 NVL72 delivers 291% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | GB300 NVL72:6594.1MI300X:1248.6 | GB300 NVL72:3815.9MI300X:778.8 | GB300 NVL72:1610.0MI300X:411.9 |
| Cost ($/M tok) | GB300 NVL72:$0.114MI300X:$0.250 | GB300 NVL72:$0.197MI300X:$0.402 | GB300 NVL72:$0.479MI300X:$0.747 |
| tok/s/MW | GB300 NVL72:3140047MI300X:697553 | GB300 NVL72:1817105MI300X:435091 | GB300 NVL72:766668MI300X:230105 |
| Concurrency | GB300 NVL72:~752MI300X:~63 | GB300 NVL72:~353MI300X:~26 | GB300 NVL72:~64MI300X:~11 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.