MiniMax M2.5/M2.7 · Chip comparison

MiniMax M2.5/M2.7 — H100 vs MI300X

Head-to-head AI inference benchmark comparison of H100 (NVIDIA Hopper) 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.

H100 / MI300X on MiniMax M2.5/M2.7 at 37 tok/s/user: 2,154 / 1,530 tok/s/chip, $0.15 / $0.17 per million tokens. H100 is 13% cheaper per token; H100 delivers 41% more tok/s/chip.

Around the middle of the 21–84 tok/s/user interactivity band, at 53 tok/s/user on MiniMax M2.5/M2.7: H100 runs 1,601 tok/s/chip at $0.20 per million tokens, MI300X runs 1,329 at $0.20. MI300X is 2% cheaper per token; H100 delivers 20% more tok/s/chip.

Setting 69 tok/s/user as the target on MiniMax M2.5/M2.7, H100 produces 1,200 tok/s/chip ($0.27 per million tokens) and MI300X produces 1,028 ($0.26). MI300X is 5% cheaper per token; H100 delivers 17% 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.)

View performance per dollar →

MI300X vs H100: full specs & benchmarks across models →

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)
H1002,154MI300X1,530
H1001,601MI300X1,329
H1001,200MI300X1,028
Cost ($/M tok)
H100$0.15MI300X$0.17
H100$0.20MI300X$0.20
H100$0.27MI300X$0.26
tok/s/MW
H1001,571,951MI300X1,100,391
H1001,168,512MI300X955,941
H100875,835MI300X739,905
Concurrency
H100~52MI300X~12
H100~28MI300X~5
H100~16MI300X~4