DeepSeek V4 Pro 1.6T — B300 vs MI300X
Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and MI300X (AMD CDNA 3) on DeepSeek V4 Pro 1.6T. Latency, throughput, and cost across LLM workloads. Use the chart controls below to switch sequences, precisions, and metrics — same interactions as the main inference chart.
B300: 2522 tok/s/GPU, $0.26 per million tokens at 70 tok/s/user on DeepSeek V4 Pro 1.6T. MI300X is unmeasured here.
At 137 tok/s/user on DeepSeek V4 Pro 1.6T, B300 delivers 1133 tok/s/GPU at $0.57 per million tokens; MI300X hasn't been benchmarked at this target.
B300 hits 421 tok/s/GPU for $1.55 per million tokens at 203 tok/s/user on DeepSeek V4 Pro 1.6T. No MI300X data at this operating point. (Numbers reflect the default 8k/1k · fp4 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B300:2521.7MI300X:— | B300:1132.8MI300X:— | B300:420.6MI300X:— |
| Cost ($/M tok) | B300:$0.262MI300X:— | B300:$0.572MI300X:— | B300:$1.549MI300X:— |
| tok/s/MW | B300:1327233MI300X:— | B300:596225MI300X:— | B300:221352MI300X:— |
| Concurrency | B300:~27MI300X:— | B300:~4MI300X:— | B300:~1MI300X:— |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.