Qwen 3.5 397B-A17B · GPU comparison

Qwen 3.5 397B-A17B — B300 vs RTX PRO 6000

Head-to-head AI inference benchmark comparison of B300 (NVIDIA Blackwell) and RTX PRO 6000 (NVIDIA Blackwell) 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.

B300 posts 13827 tok/s/GPU for $0.05 per million tokens at 58 tok/s/user on Qwen 3.5 397B-A17B; RTX PRO 6000 posts 956 tok/s/GPU for $0.12. B300 is 151% cheaper per token; B300 delivers 1347% more tok/s/GPU.

Throughput at 90 tok/s/user on Qwen 3.5 397B-A17B: B300 hits 10269 tok/s/GPU, RTX PRO 6000 hits 742. Per-million costs land at $0.06 and $0.16 respectively. B300 is 153% cheaper per token; B300 delivers 1284% more tok/s/GPU.

B300 / RTX PRO 6000 on Qwen 3.5 397B-A17B at 122 tok/s/user: 7929 / 511 tok/s/GPU, $0.08 / $0.26 per million tokens. B300 is 213% cheaper per token; B300 delivers 1451% more tok/s/GPU. (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.)

View performance-per-dollar view →

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)
Throughput (tok/s/gpu)
B300:13826.8RTX PRO 6000:955.6
B300:10268.6RTX PRO 6000:741.7
B300:7928.5RTX PRO 6000:511.2
Cost ($/M tok)
B300:$0.047RTX PRO 6000:$0.118
B300:$0.063RTX PRO 6000:$0.160
B300:$0.082RTX PRO 6000:$0.257
tok/s/MW
B300:7277287RTX PRO 6000:980065
B300:5404550RTX PRO 6000:760737
B300:4172897RTX PRO 6000:524318
Concurrency
B300:~57RTX PRO 6000:~9
B300:~28RTX PRO 6000:~4
B300:~16RTX PRO 6000:~2

Inference Performance

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

Vendor:
Deployment:
Spec Decoding: