Back to Models

Nemotron nano 9b v2

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems.

Thinking Mode
Parameters
30000000000 B
Context
256,000 tokens
Released
Invalid Date

Leaderboards

Performance vs. Industry Average

Intelligence

Nemotron nano 9b v2 is of lower intelligence compared to average (4.1), with an intelligence score of 4.0.

Price

Nemotron nano 9b v2 is cheaper compared to average ($4.58 per 1M Tokens) with a price of $0.00 per 1M Tokens.

Latency

Nemotron nano 9b v2 has a lower average latency compared to average (116.45s), with an average latency of 30.08s.

P99 Latency

Nemotron nano 9b v2 has a lower P99 latency compared to average (339.37s), taking 97.87s to receive the first token at P99 (TTFT).

Context Window

Nemotron nano 9b v2 has a smaller context window than average (351k tokens), with a context window of 256k tokens.

Nemotron nano 9b v2 - AutoBench