MiniMax M2.5/M2.7 · GPU comparison

MiniMax M2.5/M2.7 — B300 vs GB300 NVL72

Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and GB300 NVL72 (NVIDIA Blackwell) 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.

B300 posts 6798 tok/s/GPU for $0.10 per million tokens at 69 tok/s/user on MiniMax M2.5/M2.7; GB300 NVL72 posts 8401 tok/s/GPU for $0.08. GB300 NVL72 is 15% cheaper per token; GB300 NVL72 delivers 24% more tok/s/GPU.

Throughput at 108 tok/s/user on MiniMax M2.5/M2.7: B300 hits 2787 tok/s/GPU, GB300 NVL72 hits 3059. Per-million costs land at $0.23 and $0.24 respectively. B300 is 3% cheaper per token; GB300 NVL72 delivers 10% more tok/s/GPU.

B300 / GB300 NVL72 on MiniMax M2.5/M2.7 at 147 tok/s/user: 1054 / 1009 tok/s/GPU, $0.62 / $0.73 per million tokens. B300 is 18% cheaper per token; B300 delivers 4% more tok/s/GPU. (Numbers reflect the default 1k/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)
B300:6797.7GB300 NVL72:8401.0
B300:2786.7GB300 NVL72:3058.6
B300:1053.8GB300 NVL72:1008.6
Cost ($/M tok)
B300:$0.097GB300 NVL72:$0.084
B300:$0.233GB300 NVL72:$0.241
B300:$0.618GB300 NVL72:$0.727
tok/s/MW
B300:3132577GB300 NVL72:4000464
B300:1284190GB300 NVL72:1456484
B300:485618GB300 NVL72:480294
Concurrency
B300:~395GB300 NVL72:~1024
B300:~72GB300 NVL72:~121
B300:~9GB300 NVL72:~22

Inference Performance

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