MiniMax M2.5/M2.7 — B200 vs MI300X
Head-to-head AI inference benchmark comparison of B200 (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.
Throughput at 31 tok/s/user on MiniMax M2.5/M2.7: B200 hits 12194 tok/s/GPU, MI300X hits 1563. Per-million costs land at $0.04 and $0.20 respectively. B200 is 347% cheaper per token; B200 delivers 680% more tok/s/GPU.
B200 / MI300X on MiniMax M2.5/M2.7 at 49 tok/s/user: 8355 / 1396 tok/s/GPU, $0.06 / $0.22 per million tokens. B200 is 244% cheaper per token; B200 delivers 498% more tok/s/GPU.
Toward the upper edge of the 14–84 tok/s/user interactivity band, at 67 tok/s/user on MiniMax M2.5/M2.7: B200 runs 4668 tok/s/GPU at $0.12/M tokens, MI300X runs 1067 at $0.29/M. B200 is 153% cheaper per token; B200 delivers 338% more tok/s/GPU. (Numbers reflect the default 8k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B200:12194.1MI300X:1563.4 | B200:8354.6MI300X:1396.3 | B200:4668.0MI300X:1066.7 |
| Cost ($/M tok) | B200:$0.044MI300X:$0.199 | B200:$0.065MI300X:$0.223 | B200:$0.116MI300X:$0.293 |
| tok/s/MW | B200:5619378MI300X:873388 | B200:3850044MI300X:780040 | B200:2151134MI300X:595942 |
| Concurrency | B200:~1019MI300X:~18 | B200:~128MI300X:~6 | B200:~16MI300X:~4 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.