llm-benchmarks
githubdrose.io

Ministral 3 8B 2512 Benchmarks


Measured on mistral

2 runs
mistral site
Avg Tokens / Second
37.30
Decode Tokens / Second
—
Avg Time to First Token (ms)
1190.00
Runs Analysed
2
Last Updated
Nov 3, 2026, 08:37 AM

Throughput distribution

Throughput over time

Ministral 3 8B 2512mistral37tok/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 53 tok/s (99th percentile) · dashed rule is the model's own mean · 1 cell carry fewer than 4 samples

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
mistralvia OpenRouter37.3024.4050.301190.002

Frequently Asked Questions

How fast is Ministral 3 8B 2512?
The latest rolling average throughput is 37.30 tokens per second with an average time to first token of 1190.00 ms across 2 recent runs.
How often are these benchmarks updated?
Benchmarks refresh automatically whenever the monitoring cron runs. The most recent run completed on Nov 3, 2026, 08:37 AM.