Benchmark Overview
24.80
630.00
1397
Jun 13, 2026, 02:14 AM
Key Insights
llama-3.1-70b streams at 24.80 tokens/second on average across the last 1397 benchmark runs.
Performance fluctuated by 24.25 tokens/second (97.8% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 630.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on Jun 13, 2026, 02:14 AM based on 1397 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 | 24.80 | 1.55 | 25.80 | 630.00 |
Frequently Asked Questions
The latest rolling average throughput is 24.80 tokens per second with an average time to first token of 630.00 ms across 1397 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 13, 2026, 02:14 AM.