Benchmark Overview
234.00
0.22
500
Oct 15, 2025, 04:32 PM
Key Insights
llama-4-maverick-17b streams at 234.00 tokens/second on average across the last 500 benchmark runs.
Performance fluctuated by 298.30 tokens/second (127.5% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 0.22 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Oct 15, 2025, 04:32 PM based on 500 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.
llama-4-maverick-17b
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| cerebras | llama-4-maverick-17b | 234.00 | 10.70 | 309.00 | 0.22 |
Frequently Asked Questions
The latest rolling average throughput is 234.00 tokens per second with an average time to first token of 0.22 ms across 500 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 15, 2025, 04:32 PM.