llm-benchmarks
githubdrose.io

Qwen3 32B Benchmarks


Measured on openrouter

4 runs
Avg Tokens / Second
10.40
Avg Time to First Token (ms)
10100.00
Runs Analysed
4
Last Updated
Aug 18, 2026, 12:39 AM

Throughput distribution

Throughput over time

Qwen3 32Bopenrouter0tok/s

Generated throughput, including reasoning tokens — so a thinking model's line does not collapse; the table ranks on visible tokens · one cell per model, showing its best-covered provider · shared vertical scale, 0 to 1 tok/s (99th percentile) · dashed rule is the model's own mean · 1 samples above the ceiling drawn at it

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
openrouterQwen3 32B10.402.2229.5010100.00

Frequently Asked Questions

How fast is Qwen3 32B?
The latest rolling average throughput is 10.40 tokens per second with an average time to first token of 10100.00 ms across 4 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 18, 2026, 12:39 AM.

Related models