Benchmark Overview
54.50
1600.00
240
Mar 27, 2026, 12:01 AM
Key Insights
llama-3.3-70b streams at 54.50 tokens/second on average across the last 240 benchmark runs.
Performance fluctuated by 106.67 tokens/second (195.7% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 1600.00 ms (moderate latency), consider alternatives for latency-sensitive workloads.
Latest measurements completed on Mar 27, 2026, 12:01 AM based on 240 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 | 54.50 | 1.33 | 108.00 | 1600.00 |
Frequently Asked Questions
The latest rolling average throughput is 54.50 tokens per second with an average time to first token of 1600.00 ms across 240 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Mar 27, 2026, 12:01 AM.