- Avg Tokens / Second
- 11.50
- Decode Tokens / Second
- —
- Avg Time to First Token (ms)
- 4630.00
- Runs Analysed
- 1
- Last Updated
- Sep 6, 2026, 06:28 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 85 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 |
|---|---|---|---|---|---|---|
| deepinfra | via OpenRouter | 11.50 | 11.50 | 11.50 | 4630.00 | 1 |
| deepinfra | direct | 9.87 | 4.91 | 13.40 | 6400.00 | 4 |
Frequently Asked Questions
How fast is Qwen3.8 2.4T A95B?
The latest rolling average throughput is 11.50 tokens per second with an average time to first token of 4630.00 ms across 1 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 6, 2026, 06:28 PM.