Llama 3.3 70B · Performance per Dollar

Llama 3.3 70B — MI300X vs MI325X Performance per Dollar

Cost per million tokens of MI300X (AMD CDNA 3) versus MI325X (AMD CDNA 3) on Llama 3.3 70B. 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.

On Llama 3.3 70B at 48 tok/s/user, the per-million math comes out to $0.24 for MI300X and $0.22 for MI325X; MI325X delivers 11% more output per dollar.

At 69 tok/s/user on Llama 3.3 70B, MI300X costs $0.41 per million tokens; MI325X costs $0.37. MI325X is 12% more cost-efficient at this operating point.

MI325X edges MI300X at 91 tok/s/user on Llama 3.3 70B — $0.62 per million tokens versus $0.77, a 25% cost-per-token gap. (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): MI300X $1.12/GPU/hr · MI325X $1.28/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.

View full latency + throughput comparison →

Interpolated from real benchmark data. Edit target interactivity values below to compare at different operating points.
Metric
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Interactivity (tok/s/user)
Dollar per Million Tokens
MI300X:$0.239MI325X:$0.215
MI300X:$0.410MI325X:$0.366
MI300X:$0.771MI325X:$0.618
Concurrency
MI300X:~61MI325X:~62
MI300X:~32MI325X:~63
MI300X:~18MI325X:~26

Inference Performance

Inference performance metrics across different models, hardware configurations, and serving parameters.