Benchmark Overview
206.00
120.00
214
Feb 8, 2026, 09:01 PM
Key Insights
llama-3.3-70b streams at 206.00 tokens/second on average across the last 214 benchmark runs.
Performance fluctuated by 200.50 tokens/second (97.3% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 120.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Feb 8, 2026, 09:01 PM based on 214 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 | 206.00 | 79.50 | 280.00 | 120.00 |
Frequently Asked Questions
The latest rolling average throughput is 206.00 tokens per second with an average time to first token of 120.00 ms across 214 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Feb 8, 2026, 09:01 PM.