Benchmark Overview
94.40
540.00
1396
Jun 12, 2026, 03:58 PM
Key Insights
llama-3.1-8b streams at 94.40 tokens/second on average across the last 1396 benchmark runs.
Performance fluctuated by 105.94 tokens/second (112.2% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 540.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on Jun 12, 2026, 03:58 PM based on 1396 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) |
|---|---|---|---|---|---|
| bedrock | llama-3.1-8b | 94.40 | 3.06 | 109.00 | 540.00 |
Frequently Asked Questions
The latest rolling average throughput is 94.40 tokens per second with an average time to first token of 540.00 ms across 1396 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 12, 2026, 03:58 PM.