llm-benchmarks
githubdrose.io

Cydonia 24B V4.1 Benchmarks


Measured on parasail

43 runs
Avg Tokens / Second
29.70
Avg Time to First Token (ms)
1430.00
Runs Analysed
43
Last Updated
Sep 1, 2026, 03:07 AM

Throughput distribution

Throughput over time

Cydonia 24B V4.1parasail1tok/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 35 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)
parasailCydonia 24B V4.129.109.3244.401810.00
parasailCydonia 24B V4.130.306.6746.201050.00

Frequently Asked Questions

How fast is Cydonia 24B V4.1?
The latest rolling average throughput is 29.70 tokens per second with an average time to first token of 1430.00 ms across 43 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 1, 2026, 03:07 AM.

Related models