Back to Models

Nemotron 3 Nano 30B A3B

Nemotron 3 Nano 30B A3B is a highly efficient 31.6B total parameter MoE model activating only 3.2B parameters. It offers a 1M token context window and up to 3.3x higher throughput for agentic systems.

Thinking Mode
Parameters
31600000000 B
Context
262,000 tokens
Released
Invalid Date

Leaderboards

Average Score combining domain-specific Autobench scores; Higher is better

Performance vs. Industry Average

Intelligence

Nemotron 3 Nano 30B A3B is of lower intelligence compared to average (2.9), with an intelligence score of 2.7.

Price

Nemotron 3 Nano 30B A3B is cheaper compared to average ($0.75 per 1M Tokens) with a price of $0.08 per 1M Tokens.

Latency

Nemotron 3 Nano 30B A3B has a higher average latency compared to average (44.25s), with an average latency of 105.95s.

P99 Latency

Nemotron 3 Nano 30B A3B has a higher P99 latency compared to average (126.46s), taking 284.56s to receive the first token at P99 (TTFT).

Context Window

Nemotron 3 Nano 30B A3B has a smaller context window than average (406k tokens), with a context window of 262k tokens.

Nemotron 3 Nano 30B A3B - AutoBench