Benchmark Overview
77.40
220.00
373
May 19, 2026, 03:54 PM
Key Insights
llama-3-8b streams at 77.40 tokens/second on average across the last 373 benchmark runs.
Performance fluctuated by 28.90 tokens/second (37.3% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 220.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 19, 2026, 03:54 PM based on 373 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 | 77.40 | 54.30 | 83.20 | 220.00 |
Frequently Asked Questions
The latest rolling average throughput is 77.40 tokens per second with an average time to first token of 220.00 ms across 373 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 19, 2026, 03:54 PM.