GLM 5.3 744B — MI325X vs Vera Rubin NVL72 Performance per Dollar
Cost per million tokens of MI325X (AMD CDNA 3) versus Vera Rubin NVL72 (NVIDIA Vera Rubin) on GLM 5.3 744B. 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 →
MI325X costs $0.20 per million tokens at 18 tok/s/user on GLM 5.3 744B; we have no Vera Rubin NVL72 benchmark data at this exact target.
At 35 tok/s/user on GLM 5.3 744B, MI325X comes in at $0.25 per million tokens. Vera Rubin NVL72 hasn't been benchmarked at this operating point.
Only MI325X has cost data at 53 tok/s/user on GLM 5.3 744B — $0.25 per million tokens. Vera Rubin NVL72 is unmeasured at this target. (Numbers reflect the default agentic-traces · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
Chip pricing (owning hyperscaler): MI325X $1.10/chip/hr · Vera Rubin NVL72 $3.61/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 | MI325X:$0.200Vera Rubin NVL72:— | MI325X:$0.250Vera Rubin NVL72:— | MI325X:$0.252Vera Rubin NVL72:— |
| Concurrency | MI325X:~3Vera Rubin NVL72:— | MI325X:~2Vera Rubin NVL72:— | MI325X:~1Vera Rubin NVL72:— |
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.