MiniMax M3 428B — GB300 NVL72 vs MI325X Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus MI325X (AMD CDNA 3) on MiniMax M3 428B. Owning-hyperscaler TCO normalized by output tokens — performance per dollar across LLM workloads. Pick the more cost-efficient SKU at every target interactivity level. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.
Push MiniMax M3 428B to 56 tok/s/user and GB300 NVL72 lands at $0.04 per million tokens against MI325X's $0.38 — GB300 NVL72 pulls ahead by 858%.
GB300 NVL72: $0.05 per million tokens. MI325X: $0.55. Both at 90 tok/s/user on MiniMax M3 428B, with GB300 NVL72 1038% cheaper.
Toward the upper edge of the 22–159 tok/s/user interactivity band — at 125 tok/s/user — GB300 NVL72 runs $0.15 per million tokens on MiniMax M3 428B while MI325X runs $0.82. GB300 NVL72 is the cheaper choice by 460%. (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.)
Chip pricing (owning hyperscaler): GB300 NVL72 $2.31/chip/hr · MI325X $1.10/chip/hr. Source: SemiAnalysis Market July 2026 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | GB300 NVL72:$0.039MI325X:$0.376 | GB300 NVL72:$0.048MI325X:$0.547 | GB300 NVL72:$0.147MI325X:$0.824 |
| Concurrency | GB300 NVL72:~2048MI325X:~8 | GB300 NVL72:~1019MI325X:~4 | GB300 NVL72:~60MI325X:~3 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.