Qwen 3.5 397B-A17B · Performance per Dollar

Qwen 3.5 397B-A17B — B200 vs MI355X Performance per Dollar

Cost per million tokens of B200 (NVIDIA Blackwell) versus MI355X (AMD CDNA 4) on Qwen 3.5 397B-A17B. 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.

B200 edges MI355X at 81 tok/s/user on Qwen 3.5 397B-A17B — $0.22 per million tokens versus $0.26, a 15% cost-per-token gap.

Push Qwen 3.5 397B-A17B to 133 tok/s/user and B200 lands at $0.51 per million tokens against MI355X's $0.45 — MI355X pulls ahead by 13%.

B200: $1.02 per million tokens. MI355X: $0.78. Both at 185 tok/s/user on Qwen 3.5 397B-A17B, with MI355X 31% cheaper. (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): B200 $1.95/GPU/hr · MI355X $1.48/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
B200:$0.223MI355X:$0.257
B200:$0.512MI355X:$0.453
B200:$1.021MI355X:$0.781
Concurrency
B200:~65MI355X:~41
B200:~18MI355X:~14
B200:~6MI355X:~8

Inference Performance

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