NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning)

NVIDIA

Nvidia Nemotron Open Model License

Analysis of NVIDIA's NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.

Context

Release Date: Dec 15, 2025
Window: 1M

PricingPer 1M tokens

Input: $0.05
Output: $0.2
Blended 3:1: $0.0875

Capabilities

Speed: 67 t/s
Input
Output
Reasoning tokens

Latency

TTFT: 0.44 ms
500 token response: 7.94 s

Benchmarks

Intelligence: ●○○○○
Math: ●○○○○
Coding: ●○○○○
MMLU Pro: 57.9%
GPQA: 39.9%
HLE: 4.6%
SciCode: 23.0%
AIME: 13.3%
LiveCodeBench: 36.0%

Analysis of NVIDIA's NVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) and comparison to other AI models across key metrics including quality, price, performance (tokens per second & time to first token), context window & more.