MiniMax M3 428B — GB200 NVL72 vs GB300 NVL72
Head-to-head AI inference benchmark comparison of GB200 NVL72 (NVIDIA Blackwell) and GB300 NVL72 (NVIDIA Blackwell) on MiniMax M3 428B. 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.
GB200 NVL72 posts 4050 tok/s/chip for $0.13 per million tokens at 66 tok/s/user on MiniMax M3 428B; GB300 NVL72 posts 15821 tok/s/chip for $0.04. GB300 NVL72 is 215% cheaper per token; GB300 NVL72 delivers 291% more tok/s/chip.
Throughput at 106 tok/s/user on MiniMax M3 428B: GB200 NVL72 hits 1912 tok/s/chip, GB300 NVL72 hits 10018. Per-million costs land at $0.27 and $0.06 respectively. GB300 NVL72 is 322% cheaper per token; GB300 NVL72 delivers 424% more tok/s/chip.
GB200 NVL72 / GB300 NVL72 on MiniMax M3 428B at 147 tok/s/user: 811 / 3362 tok/s/chip, $0.64 / $0.19 per million tokens. GB300 NVL72 is 234% cheaper per token; GB300 NVL72 delivers 314% more tok/s/chip. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/chip) | GB200 NVL72:4050.0GB300 NVL72:15820.8 | GB200 NVL72:1912.4GB300 NVL72:10017.8 | GB200 NVL72:811.5GB300 NVL72:3362.0 |
| Cost ($/M tok) | GB200 NVL72:$0.128GB300 NVL72:$0.041 | GB200 NVL72:$0.270GB300 NVL72:$0.064 | GB200 NVL72:$0.637GB300 NVL72:$0.191 |
| tok/s/MW | GB200 NVL72:2165792GB300 NVL72:7462662 | GB200 NVL72:1022690GB300 NVL72:4725356 | GB200 NVL72:433944GB300 NVL72:1585842 |
| Concurrency | GB200 NVL72:~222GB300 NVL72:~2048 | GB200 NVL72:~45GB300 NVL72:~368 | GB200 NVL72:~13GB300 NVL72:~34 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.