Benchmark Overview
144.00
380.00
142
Mar 15, 2026, 12:03 AM
Key Insights
llama-3.1-8b streams at 144.00 tokens/second on average across the last 142 benchmark runs.
Performance fluctuated by 224.95 tokens/second (156.2% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 380.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Mar 15, 2026, 12:03 AM based on 142 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 | 144.00 | 3.05 | 228.00 | 380.00 |
Frequently Asked Questions
The latest rolling average throughput is 144.00 tokens per second with an average time to first token of 380.00 ms across 142 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 15, 2026, 12:03 AM.