Benchmark Overview
302.00
360.00
221
May 10, 2026, 09:05 PM
Key Insights
llama-3.1-8b streams at 302.00 tokens/second on average across the last 221 benchmark runs.
Performance fluctuated by 605.98 tokens/second (200.7% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 360.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 10, 2026, 09:05 PM based on 221 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 | 302.00 | 4.02 | 610.00 | 360.00 |
Frequently Asked Questions
The latest rolling average throughput is 302.00 tokens per second with an average time to first token of 360.00 ms across 221 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 10, 2026, 09:05 PM.