When was Nemotron Nano 9B v2 released?

Nemotron Nano 9B v2 was released on August 18, 2025 by Nvidia. This is the official Nemotron Nano 9B v2 release date tracked on LLM Stats.

How big is Nemotron Nano 9B v2?

Nemotron Nano 9B v2 has 8.9 billion parameters. It was trained on 21.1 trillion tokens. It ships as an open-weight model, so you can download and run it on your own hardware.

Who created Nemotron Nano 9B v2?

Nemotron Nano 9B v2 was created by Nvidia.

What is the license for Nemotron Nano 9B v2?

Nemotron Nano 9B v2 is released under the NVIDIA Open Model License Agreement license. This is an open-source / open-weight license that permits self-hosting.

What is the knowledge cutoff date for Nemotron Nano 9B v2?

Nemotron Nano 9B v2 has a knowledge cutoff of September 2024, meaning it was trained on data up to that point and may not know about events after it.

Where is the Nemotron Nano 9B v2 paper or technical report?

Nemotron Nano 9B v2 has a paper or technical report available at https://arxiv.org/abs/2508.14444. Use that source for architecture, training, release and evaluation details.

What models should I compare Nemotron Nano 9B v2 against?

Common Nemotron Nano 9B v2 comparisons include Nemotron Nano 9B v2 vs Llama 3.1 Nemotron Ultra 253B v1, Nemotron Nano 9B v2 vs DeepSeek R1 Distill Qwen 32B, Nemotron Nano 9B v2 vs Qwen3.5-9B. Compare them side by side for benchmark scores, pricing, context window, latency and API availability.

Nemotron Nano 9B v2 API Pricing, Context Window & Benchmarks

Name: Nemotron Nano 9B v2
Author: Nvidia

Nemotron Nano 9B v2: API Pricing, Context Window & Benchmarks

Nemotron Nano 9B v2 is a language model from Nvidia, released in August 2025.

NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning

Nemotron Nano 9B v2 benchmarks

Capability tiers

Standing within each category, adjusted for leaderboard depth.

Real tasks performance

How Nemotron Nano 9B v2 performs across real-world prompt categories.

Performance by conversation depth

How Nemotron Nano 9B v2 holds up as conversations get longer.

Quality Tracker

Nemotron Nano 9B v2 Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

llm-stats.com - Tue Aug 25 2026

Notice missing or incorrect data?

Nemotron Nano 9B v2 model size

Nemotron Nano 9B v2 has 8.9 billion parameters and was trained on 21.1 trillion tokens. See how it compares to other models in the same parameter range.

ParametersTraining tokens

8.9B

21.1Ttokens

2371× tokens-to-params ratio

Small (3–10B)

8.9B

1B7B70B405B

Nemotron Nano 9B v2 API

API availability not verified

API availability for Nemotron Nano 9B v2 has not been verified. It is not currently routed through the LLM Stats gateway.

Nemotron Nano 9B v2 latency

Nemotron Nano 9B v2 time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.

Nemotron Nano 9B v2 examples

Recent arena outputs from Nemotron Nano 9B v2, picked from the highest-ranked matchups.

Nemotron Nano 9B v2 license

Nemotron Nano 9B v2 is released under the NVIDIA Open Model License Agreement license, which permits commercial use, has 8.9B parameters, has a knowledge cutoff of September 2024.

License: NVIDIA Open Model License Agreement; Commercial use allowed
Parameters: 8.9B
Knowledge cutoff: September 2024

NVIDIA Open Model License Agreement

Nemotron Nano 9B v2 resources

Official sources for Nemotron Nano 9B v2: official playground, paper or system card, official launch post, model weights.

Nemotron Nano 9B v2 vs other models

The most-compared alternatives to Nemotron Nano 9B v2 are Llama 3.1 Nemotron Ultra 253B v1, DeepSeek R1 Distill Qwen 32B, Qwen3.5-9B. Open any pair side-by-side for benchmarks, pricing, context, and latency.