nemotron-3-ultra tokens per second
Live benchmark data for nemotron-3-ultra on ollama. Speed, latency, and reliability — benchmarked every ~10 minutes.
- Latest TPS
- 12.2 tok/s
- 24h avg TPS
- 18.7 tok/s
- TTFT
- 4.2s
- 24h reliability
- 98%
- Last tested
- 12m 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 →