Benchmark Overview
173.00
180.00
226
May 10, 2026, 09:16 PM
Key Insights
llama-3.3-70b streams at 173.00 tokens/second on average across the last 226 benchmark runs.
Performance fluctuated by 289.40 tokens/second (167.3% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 180.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on May 10, 2026, 09:16 PM based on 226 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) |
|---|---|---|---|---|---|
| groq | llama-3.3-70b | 173.00 | 24.60 | 314.00 | 180.00 |
Frequently Asked Questions
The latest rolling average throughput is 173.00 tokens per second with an average time to first token of 180.00 ms across 226 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 10, 2026, 09:16 PM.