Benchmark Overview
70.10
0.49
30
Sep 25, 2025, 09:31 PM
Key Insights
llama-3.1-8b streams at 70.10 tokens/second on average across the last 30 benchmark runs.
Performance fluctuated by 89.80 tokens/second (128.1% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 0.49 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Sep 25, 2025, 09:31 PM based on 30 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) |
|---|---|---|---|---|---|
| lambda | llama-3.1-8b | 70.10 | 15.20 | 105.00 | 0.49 |
Frequently Asked Questions
The latest rolling average throughput is 70.10 tokens per second with an average time to first token of 0.49 ms across 30 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 25, 2025, 09:31 PM.