Qwen 3.5 397B-A17B · Performance per Dollar

Qwen 3.5 397B-A17B — H100 vs MI325X Performance per Dollar

Cost per million tokens of H100 (NVIDIA Hopper) versus MI325X (AMD CDNA 3) 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.

H100 edges MI325X at 52 tok/s/user on Qwen 3.5 397B-A17B — $1.20 per million tokens versus $1.36, a 14% cost-per-token gap.

Push Qwen 3.5 397B-A17B to 59 tok/s/user and H100 lands at $1.38 per million tokens against MI325X's $1.83 — H100 pulls ahead by 33%.

H100: $1.55 per million tokens. MI325X: $3.09. Both at 66 tok/s/user on Qwen 3.5 397B-A17B, with H100 100% 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): H100 $1.30/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
H100:$1.198MI325X:$1.363
H100:$1.378MI325X:$1.833
H100:$1.548MI325X:$3.094
Concurrency
H100:~25MI325X:~22
H100:~19MI325X:~14
H100:~14MI325X:~7

Inference Performance

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