Benchmark Overview
35.50
330.00
3
Jan 2, 2026, 03:03 AM
Key Insights
llama-3.3-70b streams at 35.50 tokens/second on average across the last 3 benchmark runs.
Performance fluctuated by 15.40 tokens/second (43.4% coefficient of variation), indicating variable behavior across benchmark runs.
Average time to first token is 330.00 ms (excellent latency), suitable for latency-sensitive workloads.
Latest measurements completed on Jan 2, 2026, 03:03 AM based on 3 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) |
|---|---|---|---|---|---|
| deepinfra | llama-3.3-70b | 35.50 | 27.20 | 42.60 | 330.00 |
Frequently Asked Questions
The latest rolling average throughput is 35.50 tokens per second with an average time to first token of 330.00 ms across 3 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Jan 2, 2026, 03:03 AM.