Muse Spark Open 816B — GB300 NVL72 vs MI355X Performance per Dollar
Cost per million tokens of GB300 NVL72 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) on Muse Spark Open 816B. Large-hyperscaler-volume ownership TCO normalized by total 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.
AgentX replays real coding-agent sessions rather than fixed-length prompts, so context grows turn over turn and most of each request is served from cache instead of being recomputed. That turns the comparison into a systems question: KV transfer between nodes, prefix-aware routing, and cache capacity all move the curve alongside raw chip throughput. Fixed-sequence workloads stay the clean baseline for kernel and silicon performance, so the two scenarios answer different questions about the same hardware. Learn more about AgentX →
Near the low end of the 30–184 tok/s/user interactivity band — at 68 tok/s/user — GB300 NVL72 runs $0.03 per million tokens on Muse Spark Open 816B while MI355X runs $0.05. GB300 NVL72 is the cheaper choice by 62%.
On Muse Spark Open 816B at 107 tok/s/user, the per-million math comes out to $0.03 for GB300 NVL72 and $0.08 for MI355X; GB300 NVL72 delivers 140% more total tokens per dollar.
At 145 tok/s/user on Muse Spark Open 816B, GB300 NVL72 costs $0.04 per million tokens; MI355X costs $0.15. GB300 NVL72 is 311% more cost-efficient at this operating point. (Numbers reflect the default agentic-traces · fp4 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 · MI355X $1.50/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:$0.029MI355X:$0.046 | GB300 NVL72:$0.032MI355X:$0.077 | GB300 NVL72:$0.036MI355X:$0.150 |
| Concurrency | GB300 NVL72:~19MI355X:~15 | GB300 NVL72:~15MI355X:~10 | GB300 NVL72:~13MI355X:~1 |
Inference Performance
Agentic inference metrics from the AgentX scenario and fixed-sequence inference metrics across models, hardware configurations, and serving parameters.
No data available
No measurements to plot for this selection. Review the benchmark controls above or adjust quick filters.