Measured on alibaba
5 runs- Avg Tokens / Second
- 9.72
- Avg Time to First Token (ms)
- 5935.00
- Runs Analysed
- 5
- Last Updated
- Sep 1, 2026, 04:08 AM
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 · shared vertical scale, 0 to 33 tok/s (99th percentile) · dashed rule is the model's own mean · 1 further provider not drawn
Every provider serving this model
2 measured| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| alibaba | Qwen3.8 Max | 7.25 | 5.28 | 11.10 | 7940.00 |
| alibaba | Qwen3.8 Max | 12.20 | 12.20 | 12.20 | 3930.00 |
Frequently Asked Questions
How fast is Qwen3.8 Max?
The latest rolling average throughput is 9.72 tokens per second with an average time to first token of 5935.00 ms across 5 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, 04:08 AM.