llm-benchmarks
githubdrose.io

Beam 1.0 501B A23B Benchmarks


Measured on digitalocean

6 runs
Avg Tokens / Second
40.60
Decode Tokens / Second
—
Avg Time to First Token (ms)
1500.00
Runs Analysed
6
Last Updated
Oct 31, 2026, 05:32 PM

Throughput distribution

Throughput over time

Beam 1.0 501B A23Bdigitalocean141tok/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 · models with at least 4 samples in the window first, fastest of those at the top · shared vertical scale, 0 to 188 tok/s (99th percentile) · dashed rule is the model's own mean

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
digitaloceanvia OpenRouter40.6020.7063.001500.006

Frequently Asked Questions

How fast is Beam 1.0 501B A23B?
The latest rolling average throughput is 40.60 tokens per second with an average time to first token of 1500.00 ms across 6 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Oct 31, 2026, 05:32 PM.

Related models