Benchmark Overview
40.10
710.00
173
May 15, 2026, 12:25 AM
Key Insights
llama-3.3-70b streams at 40.10 tokens/second on average across the last 173 benchmark runs.
Performance fluctuated by 63.63 tokens/second (158.7% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 710.00 ms (good latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 15, 2026, 12:25 AM based on 173 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-3.3-70b
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| fireworks | llama-3.3-70b | 40.10 | 5.57 | 69.20 | 710.00 |
Frequently Asked Questions
The latest rolling average throughput is 40.10 tokens per second with an average time to first token of 710.00 ms across 173 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 15, 2026, 12:25 AM.