Benchmark Overview
147.00
220.00
84
Mar 15, 2026, 12:03 AM
Key Insights
llama-3.1-8b streams at 147.00 tokens/second on average across the last 84 benchmark runs.
Performance fluctuated by 187.00 tokens/second (127.2% 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 Mar 15, 2026, 12:03 AM based on 84 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) |
|---|---|---|---|---|---|
| together | llama-3.1-8b | 147.00 | 41.00 | 228.00 | 220.00 |
Frequently Asked Questions
The latest rolling average throughput is 147.00 tokens per second with an average time to first token of 220.00 ms across 84 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 15, 2026, 12:03 AM.