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 41 tok/s/user and GB300 NVL72 lands at $0.40 per million tokens against MI325X's $0.48 — GB300 NVL72 pulls ahead by 18%.
GB300 NVL72: $1.55 per million tokens. MI325X: $1.19. Both at 75 tok/s/user on MiniMax M3 428B, with MI325X 31% cheaper.
Toward the upper edge of the 8–142 tok/s/user interactivity band — at 109 tok/s/user — GB300 NVL72 runs $3.79 per million tokens on MiniMax M3 428B while MI325X runs $2.08. MI325X is the cheaper choice by 82%. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
GPU pricing (owning hyperscaler): GB300 NVL72 $2.65/GPU/hr · MI325X $1.28/GPU/hr. Source: SemiAnalysis Market August 2025 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:$0.404MI325X:$0.476 | GB300 NVL72:$1.552MI325X:$1.186 | GB300 NVL72:$3.791MI325X:$2.079 |
| Concurrency | GB300 NVL72:~243MI325X:~80 | GB300 NVL72:~22MI325X:~18 | GB300 NVL72:~5MI325X:~6 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.