Haimaker.ai Logo

Inference Benchmarks

Performance metrics across hardware, software, and model configurations

Back to Home

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

Qwen3-32B
Clear
Active Filters:Tag: Qwen3-32B

Found 1 benchmark suite

DateSuite NameGPUModelOutput TPSInput TPSEnergy Cost
(kWh/MT)
2/19/2026
Tenstorrent Wormhole (32x) - Qwen3-32B
Wormhole
32x 384GB
Qwen3-32B
qwen
1,438.105,640.690.11