MiniMax M3 428B — GB300 NVL72 vs MI300X Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus MI300X (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.
GB300 NVL72: $0.49 per million tokens. MI300X: $0.57. Both at 45 tok/s/user on MiniMax M3 428B, with GB300 NVL72 16% cheaper.
Around the middle of the 13–142 tok/s/user interactivity band — at 77 tok/s/user — GB300 NVL72 runs $1.61 per million tokens on MiniMax M3 428B while MI300X runs $1.50. MI300X is the cheaper choice by 7%.
On MiniMax M3 428B at 110 tok/s/user, the per-million math comes out to $3.90 for GB300 NVL72 and $2.00 for MI300X; MI300X delivers 94% more output per dollar. (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 · MI300X $1.12/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:$0.493MI300X:$0.570 | GB300 NVL72:$1.611MI300X:$1.502 | GB300 NVL72:$3.895MI300X:$2.003 |
| Concurrency | GB300 NVL72:~177MI300X:~51 | GB300 NVL72:~20MI300X:~12 | GB300 NVL72:~5MI300X:~6 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.