llm-benchmarks
githubdrose.io

Rocinante 12B Benchmarks


Measured on parasail

39 runs
Avg Tokens / Second
34.95
Avg Time to First Token (ms)
680.00
Runs Analysed
39
Last Updated
Aug 18, 2026, 06:27 PM

Throughput distribution

Throughput over time

Rocinante 12Bparasail1tok/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 37 tok/s (99th percentile) · dashed rule is the model's own mean · 1 further provider not drawn · 1 samples above the ceiling drawn at it

Every provider serving this model

2 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
parasailRocinante 12B35.0029.4040.00670.00
parasailRocinante 12B34.9013.0065.40690.00

Frequently Asked Questions

How fast is Rocinante 12B?
The latest rolling average throughput is 34.95 tokens per second with an average time to first token of 680.00 ms across 39 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Aug 18, 2026, 06:27 PM.

Related models