by Nvidia

Nemotron Nano 9B V2.

text open weights laptop+ 9B params 131K ctx
Cheapest input
$0.06/M
on Together AI
Cheapest output
$0.25/M
on Together AI
Smallest GPU
1× Nvidia GeForce RTX 3050
$0.022/hr

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...

Smallest GPU to run it See all quantisations →

1× Nvidia GeForce RTX 3050 · $0.022/hr.

Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.

Where to use it

Cheapest hosted endpoints.

Provider Access $/M in $/M out
Together AI hosted inference $0.06 $0.25 Launch ↗
Sources

Official references.

Family

Variants in the Nemotron family.

FAQ

Frequently asked.

How do I run Nemotron Nano 9B V2?
Nemotron Nano 9B V2 is open-weight, so you can self-host on rented GPUs. See the Run It Yourself tab for GPU configurations + cost estimates, or use one of the hosted inference providers listed on this page.
Where can I access Nemotron Nano 9B V2?
Nemotron Nano 9B V2 is available via Together AI. Each access option lists its own pricing (per million tokens or hourly hosting).
How much does it cost to run Nemotron Nano 9B V2?
API pricing starts at $0.06/M input tokens and $0.25/M output tokens. Self-hosting cost depends on the GPU you rent — see the Run It Yourself tab.
Is Nemotron Nano 9B V2 open-source or proprietary?
Nemotron Nano 9B V2 is open-weight under the nvidia-open-model-license license. You can download and self-host it.