Benchmark Overview
81.70
0.20
1166
Dec 26, 2025, 02:53 AM
Key Insights
llama-3-8b streams at 81.70 tokens/second on average across the last 1166 benchmark runs.
Performance fluctuated by 82.57 tokens/second (101.1% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 0.20 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Dec 26, 2025, 02:53 AM based on 1166 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-3-8b
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| bedrock | llama-3-8b | 81.70 | 7.03 | 89.60 | 0.20 |
Frequently Asked Questions
The latest rolling average throughput is 81.70 tokens per second with an average time to first token of 0.20 ms across 1166 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Dec 26, 2025, 02:53 AM.