llm-benchmarks
githubdrose.io

nvidia/NVIDIA-Nemotron-3.5-Lightning Benchmarks


Measured on deepinfra

4 runs
deepinfra site
Avg Tokens / Second
191.00
Avg Time to First Token (ms)
0.00
Runs Analysed
4
Last Updated
Aug 12, 2026, 04:09 PM

Throughput distribution

  • nvidia/NVIDIA-Nemotron-3.5-Lightning deepinfra191 tok/s
050100150200250

Visible-token throughput, same basis as the table · curves normalised per model

Throughput over time

nvidia/NVIDIA-Nemotron-3.5-Lightningdeepinfra1tok/s

Generated throughput, including reasoning tokens — so a thinking model's line does not collapse; the table ranks on visible tokens · one cell per model, showing its best-covered provider · shared vertical scale, 0 to 1 tok/s (99th percentile) · dashed rule is the model's own mean · 1 samples above the ceiling drawn at it

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
deepinfranvidia/NVIDIA-Nemotron-3.5-Lightning191.00130.00233.000.00

Frequently Asked Questions

How fast is nvidia/NVIDIA-Nemotron-3.5-Lightning?
The latest rolling average throughput is 191.00 tokens per second with an average time to first token of 0.00 ms across 4 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 12, 2026, 04:09 PM.