Benchmark Overview
192.00
280.00
3
Jun 30, 2026, 04:34 PM
Key Insights
gemma-4-31b streams at 192.00 tokens/second on average across the last 3 benchmark runs.
Performance fluctuated by 8.00 tokens/second (4.2% coefficient of variation), indicating consistent behavior across benchmark runs.
Average time to first token is 280.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Jun 30, 2026, 04:34 PM based on 3 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 | 192.00 | 189.00 | 197.00 | 280.00 |
Frequently Asked Questions
The latest rolling average throughput is 192.00 tokens per second with an average time to first token of 280.00 ms across 3 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 30, 2026, 04:34 PM.