Nemotron 3 Ultra (Free) tokens per second

Live benchmark data for Nemotron 3 Ultra (Free) on opencode-zen. Speed, latency, and reliability — benchmarked every ~10 minutes.

Latest TPS
9.1 tok/s
24h avg TPS
15.3 tok/s
TTFT
32.9s
24h reliability
55%
Last tested
6m 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 →