Qwen 3.5 397B-A17B — B300 vs H100 Performance per Dollar
Cost per million tokens of B300 (NVIDIA Blackwell) versus H100 (NVIDIA Hopper) 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.
Near the low end of the 45–110 tok/s/user interactivity band — at 61 tok/s/user — B300 runs $0.20 per million tokens on Qwen 3.5 397B-A17B while H100 runs $1.43. B300 is the cheaper choice by 621%.
On Qwen 3.5 397B-A17B at 78 tok/s/user, the per-million math comes out to $0.26 for B300 and $1.78 for H100; B300 delivers 589% more output per dollar.
At 94 tok/s/user on Qwen 3.5 397B-A17B, B300 costs $0.34 per million tokens; H100 costs $2.38. B300 is 591% more cost-efficient at this operating point. (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): B300 $2.34/GPU/hr · H100 $1.30/GPU/hr. Source: SemiAnalysis Market August 2025 Pricing Surveys & AI Cloud TCO Model.
| Metric | Interactivity (tok/s/user) | Interactivity (tok/s/user) | Interactivity (tok/s/user) |
|---|---|---|---|
| Dollar per Million Tokens | B300:$0.198H100:$1.429 | B300:$0.258H100:$1.779 | B300:$0.344H100:$2.381 |
| Concurrency | B300:~109H100:~17 | B300:~67H100:~10 | B300:~42H100:~7 |
Inference Performance
Inference performance metrics across different models, hardware configurations, and serving parameters.