Benchmark Overview
180.00
410.00
297
Jul 10, 2026, 12:30 AM
Key Insights
gemma-4-31b streams at 180.00 tokens/second on average across the last 297 benchmark runs.
Performance fluctuated by 213.24 tokens/second (118.5% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 410.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Jul 10, 2026, 12:30 AM based on 297 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-4-31b
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| cerebras | gemma-4-31b | 180.00 | 3.76 | 217.00 | 410.00 |
Frequently Asked Questions
The latest rolling average throughput is 180.00 tokens per second with an average time to first token of 410.00 ms across 297 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jul 10, 2026, 12:30 AM.