Benchmark Overview
319.00
90.00
239
Mar 8, 2026, 03:02 PM
Key Insights
llama-3.1-8b streams at 319.00 tokens/second on average across the last 239 benchmark runs.
Performance fluctuated by 383.10 tokens/second (120.1% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 90.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Mar 8, 2026, 03:02 PM based on 239 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 | 319.00 | 87.90 | 471.00 | 90.00 |
Frequently Asked Questions
The latest rolling average throughput is 319.00 tokens per second with an average time to first token of 90.00 ms across 239 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 8, 2026, 03:02 PM.