llm-benchmarks
githubdrose.io

Skyfall 36B V2 Benchmarks


Measured on parasail

41 runs
Avg Tokens / Second
35.80
Avg Time to First Token (ms)
765.00
Runs Analysed
41
Last Updated
Sep 1, 2026, 04:08 AM

Throughput distribution

Throughput over time

Skyfall 36B V2parasail1tok/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 49 tok/s (99th percentile) · dashed rule is the model's own mean · 1 further provider not drawn

Every provider serving this model

2 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
parasailSkyfall 36B V242.4033.3047.20630.00
parasailSkyfall 36B V229.2010.4059.30900.00

Frequently Asked Questions

How fast is Skyfall 36B V2?
The latest rolling average throughput is 35.80 tokens per second with an average time to first token of 765.00 ms across 41 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, 04:08 AM.

Related models