Measured on primeintellect
3 runs- Avg Tokens / Second
- 22.80
- Decode Tokens / Second
- —
- Avg Time to First Token (ms)
- 8560.00
- Runs Analysed
- 3
- Last Updated
- Nov 15, 2026, 07:33 PM
Throughput distribution
Throughput over time
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 · models with at least 4 samples in the window first, fastest of those at the top · shared vertical scale, 0 to 110 tok/s (99th percentile) · dashed rule is the model's own mean · 1 cell carry fewer than 4 samples
Every lane measuring this model
2 measured · live first · a lane is a provider, a catalogue id and a transport| Provider | Lane | Avg Toks/Sec | Min | Max | Avg TTF (ms) | n |
|---|---|---|---|---|---|---|
| primeintellect | direct | 22.80 | 4.37 | 58.70 | 8560.00 | 3 |
| primeintellect | via OpenRouter | 13.30 | 1.79 | 38.20 | 13100.00 | 4 |
Frequently Asked Questions
How fast is Qwen3.6 35B A3B?
The latest rolling average throughput is 22.80 tokens per second with an average time to first token of 8560.00 ms across 3 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Nov 15, 2026, 07:33 PM.