Benchmark Overview
67.90
0.00
29
Jun 13, 2026, 09:05 PM
Key Insights
Meta-Llama-3-8B-Instruct-Lite streams at 67.90 tokens/second on average across the last 29 benchmark runs.
Performance fluctuated by 106.78 tokens/second (157.3% coefficient of variation), indicating variable behavior across benchmark runs.
Latest measurements completed on Jun 13, 2026, 09:05 PM based on 29 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.
Meta-Llama-3-8B-Instruct-Lite
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| together | Meta-Llama-3-8B-Instruct-Lite | 67.90 | 7.22 | 114.00 | 0.00 |
Frequently Asked Questions
The latest rolling average throughput is 67.90 tokens per second with an average time to first token of 0.00 ms across 29 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jun 13, 2026, 09:05 PM.