Benchmark Overview
196.00
930.00
235
Mar 7, 2026, 12:00 AM
Key Insights
llama-3.1-8b streams at 196.00 tokens/second on average across the last 235 benchmark runs.
Performance fluctuated by 346.46 tokens/second (176.8% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 930.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on Mar 7, 2026, 12:00 AM based on 235 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 | 196.00 | 1.54 | 348.00 | 930.00 |
Frequently Asked Questions
The latest rolling average throughput is 196.00 tokens per second with an average time to first token of 930.00 ms across 235 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 7, 2026, 12:00 AM.