Inference Benchmarks

Performance metrics across hardware, software, and model configurations

Early Preview

We are working to certify more internal benchmarks to be published. If you're interested in providing hardware or have questions, email benchmarks@haimaker.ai.

Filters

Active Filters:Tag: qwen3-30b-a3b

Found 1 benchmark suite

Date	Suite Name	GPU	Model	Output TPS	Input TPS	Energy Cost (kWh/MT)
11/7/2025	NVIDIA H200 NVL (2x) - qwen3-30b-a3b	NVIDIA H200 NVL 2x 280GB	qwen3-30b-a3b qwen	6,124.38	51,413.77	0.00