Benchmark Overview
235.00
0.17
710
Oct 9, 2025, 01:27 AM
Key Insights
gemma-2-9b streams at 235.00 tokens/second on average across the last 710 benchmark runs.
Performance fluctuated by 256.10 tokens/second (109.0% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 0.17 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Oct 9, 2025, 01:27 AM based on 710 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.
gemma-2-9b
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| groq | gemma-2-9b | 235.00 | 28.90 | 285.00 | 0.17 |
Frequently Asked Questions
The latest rolling average throughput is 235.00 tokens per second with an average time to first token of 0.17 ms across 710 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 9, 2025, 01:27 AM.