MiniMax M2.5/M2.7 · Chip comparison

MiniMax M2.5/M2.7 — B300 vs H100

Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and H100 (NVIDIA Hopper) 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 / H100 on MiniMax M2.5/M2.7 at 44 tok/s/user: 9,991 / 1,891 tok/s/chip, $0.063 / $0.17 per million tokens. B300 is 63% cheaper per token; B300 delivers 5.3× the tok/s/chip.

Around the middle of the 21–111 tok/s/user interactivity band, at 66 tok/s/user on MiniMax M2.5/M2.7: B300 runs 5,508 tok/s/chip at $0.11 per million tokens, H100 runs 1,269 at $0.26. B300 is 56% cheaper per token; B300 delivers 4.3× the tok/s/chip.

Setting 89 tok/s/user as the target on MiniMax M2.5/M2.7, B300 produces 4,006 tok/s/chip ($0.16 per million tokens) and H100 produces 806 ($0.40). B300 is 61% cheaper per token; B300 delivers 5.0× the 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.)

View performance per dollar →

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/chip)
B3009,991H1001,891
B3005,508H1001,269
B3004,006H100806
Cost ($/M tok)
B300$0.063H100$0.17
B300$0.11H100$0.26
B300$0.16H100$0.40
tok/s/MW
B3005,258,170H1001,380,510
B3002,898,963H100926,145
B3002,108,613H100588,262
Concurrency
B300~190H100~39
B300~30H100~18
B300~4H100~9