llm-benchmarks
githubdrose.io

Qwen3.6 35B A3B Benchmarks


Measured on phala

52 runs
Avg Tokens / Second
5.57
Avg Time to First Token (ms)
11600.00
Runs Analysed
52
Last Updated
Sep 1, 2026, 12:12 PM

Throughput distribution

Throughput over time

Qwen3.6 35B A3Bparasail3tok/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 154 tok/s (99th percentile) · dashed rule is the model's own mean · 12 further providers not drawn

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
phalaQwen3.6 35B A3B5.574.056.9111600.00

Frequently Asked Questions

How fast is Qwen3.6 35B A3B?
The latest rolling average throughput is 5.57 tokens per second with an average time to first token of 11600.00 ms across 52 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 1, 2026, 12:12 PM.

Related models