llm-benchmarks
githubdrose.io

Ministral 3 8B 2512 Benchmarks


Measured on mistral

42 runs
mistral site
Avg Tokens / Second
50.45
Avg Time to First Token (ms)
830.00
Runs Analysed
42
Last Updated
Sep 1, 2026, 03:03 AM

Throughput distribution

Throughput over time

Ministral 3 8B 2512mistral4tok/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 60 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)
mistralMinistral 3 8B 251245.8023.1099.70980.00
mistralMinistral 3 8B 251255.1036.6065.30680.00

Frequently Asked Questions

How fast is Ministral 3 8B 2512?
The latest rolling average throughput is 50.45 tokens per second with an average time to first token of 830.00 ms across 42 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, 03:03 AM.