llm-benchmarks
githubdrose.io

Llama 3 8B Lunaris Benchmarks


Measured on parasail

1 runs
Avg Tokens / Second
49.80
Decode Tokens / Second
—
Avg Time to First Token (ms)
600.00
Runs Analysed
1
Last Updated
Sep 22, 2026, 05:57 AM

Throughput distribution

Throughput over time

No time series data available.

Every lane measuring this model

1 measured · live first · a lane is a provider, a catalogue id and a transport
ProviderLaneAvg Toks/SecMinMaxAvg TTF (ms)n
parasailvia OpenRouter49.8049.8049.80600.001

Frequently Asked Questions

How fast is Llama 3 8B Lunaris?
The latest rolling average throughput is 49.80 tokens per second with an average time to first token of 600.00 ms across 1 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Sep 22, 2026, 05:57 AM.

Related models