Benchmark Overview
33.10
0.00
69
May 20, 2026, 02:33 AM
Key Insights
Llama-3.3-Nemotron-Super-49B-v1.5 streams at 33.10 tokens/second on average across the last 69 benchmark runs.
Performance fluctuated by 46.05 tokens/second (139.1% coefficient of variation), indicating variable behavior across benchmark runs.
Latest measurements completed on May 20, 2026, 02:33 AM based on 69 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-Nemotron-Super-49B-v1.5
Benchmark Samples
| Provider | Model | Avg Toks/Sec | Min | Max | Avg TTF (ms) |
|---|---|---|---|---|---|
| deepinfra | Llama-3.3-Nemotron-Super-49B-v1.5 | 33.10 | 4.65 | 50.70 | 0.00 |
Frequently Asked Questions
The latest rolling average throughput is 33.10 tokens per second with an average time to first token of 0.00 ms across 69 recent runs.
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on May 20, 2026, 02:33 AM.