Benchmark Overview
152.00
490.00
15
May 16, 2026, 05:01 PM
Key Insights
llama-3.1-8b streams at 152.00 tokens/second on average across the last 15 benchmark runs.
Performance fluctuated by 146.00 tokens/second (96.1% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 490.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 16, 2026, 05:01 PM based on 15 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-3.1-8b
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| cerebras | llama-3.1-8b | 152.00 | 29.00 | 175.00 | 490.00 |
Frequently Asked Questions
The latest rolling average throughput is 152.00 tokens per second with an average time to first token of 490.00 ms across 15 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 16, 2026, 05:01 PM.