Benchmark Overview
62.40
290.00
118
May 19, 2026, 10:05 PM
Key Insights
qwen-3.5-397b-a17b streams at 62.40 tokens/second on average across the last 118 benchmark runs.
Performance fluctuated by 98.85 tokens/second (158.4% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 290.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 19, 2026, 10:05 PM based on 118 total samples.
Performance Distribution
Distribution of throughput measurements showing performance consistency across benchmark runs.
Performance Over Time
Historical performance trends showing how throughput has changed over the benchmarking period.
qwen-3.5-397b-a17b
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| deepinfra | qwen-3.5-397b-a17b | 62.40 | 4.15 | 103.00 | 290.00 |
Frequently Asked Questions
The latest rolling average throughput is 62.40 tokens per second with an average time to first token of 290.00 ms across 118 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 19, 2026, 10:05 PM.