Benchmark Overview
220.00
130.00
227
May 11, 2026, 01:46 AM
Key Insights
llama-3.1-8b streams at 220.00 tokens/second on average across the last 227 benchmark runs.
Performance fluctuated by 224.70 tokens/second (102.1% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 130.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 11, 2026, 01:46 AM based on 227 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) |
|---|---|---|---|---|---|
| groq | llama-3.1-8b | 220.00 | 85.30 | 310.00 | 130.00 |
Frequently Asked Questions
The latest rolling average throughput is 220.00 tokens per second with an average time to first token of 130.00 ms across 227 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 11, 2026, 01:46 AM.