Qwen 3.5 397B-A17B — B300 vs MI325X
Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and MI325X (AMD CDNA 3) on Qwen 3.5 397B-A17B. 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.
Throughput at 46 tok/s/user on Qwen 3.5 397B-A17B: B300 hits 4358 tok/s/GPU, MI325X hits 403. Per-million costs land at $0.15 and $0.86 respectively. B300 is 472% cheaper per token; B300 delivers 982% more tok/s/GPU.
B300 / MI325X on Qwen 3.5 397B-A17B at 55 tok/s/user: 3643 / 219 tok/s/GPU, $0.18 / $1.63 per million tokens. B300 is 811% cheaper per token; B300 delivers 1561% more tok/s/GPU.
Toward the upper edge of the 37–72 tok/s/user interactivity band, at 64 tok/s/user on Qwen 3.5 397B-A17B: B300 runs 3104 tok/s/GPU at $0.21/M tokens, MI325X runs 134 at $2.64/M. B300 is 1170% cheaper per token; B300 delivers 2212% more tok/s/GPU. (Numbers reflect the default 1k/1k · fp8 selection for this URL — table and chart below update if you change sequence, precision, or model in the controls.)
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Throughput (tok/s/gpu) | B300:4358.1MI325X:402.9 | B300:3642.8MI325X:219.4 | B300:3103.8MI325X:134.3 |
| Cost ($/M tok) | B300:$0.151MI325X:$0.864 | B300:$0.179MI325X:$1.631 | B300:$0.208MI325X:$2.638 |
| tok/s/MW | B300:2008337MI325X:184830 | B300:1678708MI325X:100633 | B300:1430318MI325X:61591 |
| Concurrency | B300:~205MI325X:~37 | B300:~140MI325X:~16 | B300:~99MI325X:~9 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.