llm-benchmarks
githubdrose.io

Qwen3.6 35B A3B Benchmarks


Measured on openrouter

37 runs
Avg Tokens / Second
6.34
Avg Time to First Token (ms)
14400.00
Runs Analysed
37
Last Updated
Aug 18, 2026, 03:13 PM

Throughput distribution

Throughput over time

Qwen3.6 35B A3Bopenrouter1tok/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 26 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)
openrouterQwen3.6 35B A3B6.340.6810.1014400.00

Frequently Asked Questions

How fast is Qwen3.6 35B A3B?
The latest rolling average throughput is 6.34 tokens per second with an average time to first token of 14400.00 ms across 37 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, 03:13 PM.

Related models