llm-benchmarks
githubdrose.io

Magnum v4 72B Benchmarks


Measured on mancer

388 runs
Avg Tokens / Second
14.70
Avg Time to First Token (ms)
1020.00
Runs Analysed
388
Last Updated
Sep 1, 2026, 03:13 AM

Throughput distribution

Throughput over time

Magnum v4 72Bmancer0tok/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 16 tok/s (99th percentile) · dashed rule is the model's own mean · 1 further provider not drawn

Every provider serving this model

1 measured
ProviderModelAvg Toks/SecMinMaxAvg TTF (ms)
mancerMagnum v4 72B14.7013.1015.501020.00

Frequently Asked Questions

How fast is Magnum v4 72B?
The latest rolling average throughput is 14.70 tokens per second with an average time to first token of 1020.00 ms across 388 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, 03:13 AM.

Related models