Benchmark Overview
72.70
490.00
238
Feb 8, 2026, 06:03 PM
Key Insights
llama-3.1-70b streams at 72.70 tokens/second on average across the last 238 benchmark runs.
Performance fluctuated by 142.91 tokens/second (196.6% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 490.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Feb 8, 2026, 06:03 PM based on 238 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) |
|---|---|---|---|---|---|
| together | llama-3.1-70b | 72.70 | 4.09 | 147.00 | 490.00 |
Frequently Asked Questions
The latest rolling average throughput is 72.70 tokens per second with an average time to first token of 490.00 ms across 238 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Feb 8, 2026, 06:03 PM.