ministral-3:3b (non-reasoning) tokens per second

Live benchmark data for ministral-3:3b (non-reasoning) on ollama. Speed, latency, and reliability — benchmarked every ~10 minutes.

Latest TPS
242.6 tok/s
24h avg TPS
192.9 tok/s
TTFT
442ms
24h reliability
100%
Last tested
9m ago

Tokens per second over time

Time to first token over time

Speed is measured as output tokens ÷ generation time. Each benchmark fires one streaming chat completion with a fixed ~300-token prompt, every ~10 minutes. Full methodology →