Benchmark Overview
25.50
0.53
36
Oct 27, 2025, 11:32 AM
Key Insights
llama-3.1-70b streams at 25.50 tokens/second on average across the last 36 benchmark runs.
Performance fluctuated by 4.00 tokens/second (15.7% coefficient of variation), indicating consistent behavior across benchmark runs.
Average time to first token is 0.53 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Oct 27, 2025, 11:32 AM based on 36 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-3.1-70b
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| bedrock | llama-3.1-70b | 25.50 | 22.20 | 26.20 | 0.53 |
Frequently Asked Questions
The latest rolling average throughput is 25.50 tokens per second with an average time to first token of 0.53 ms across 36 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 27, 2025, 11:32 AM.