NewJoin us for our inaugural conference, Forge 2026
DocsLog inGet started
NVIDIA logo

NVIDIA Nemotron Nano 12B v2

Ready
model path:accounts/fireworks/models/nvidia-nemotron-nano-12b-v2
Deploy on demand

NVIDIA-Nemotron-Nano-12B-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. To disable the reasoning trace, include /no_think in your system prompt.

NVIDIA Nemotron Nano 12B v2 API Features

On-demand Deployment

Docs

On-demand deployments allow you to use NVIDIA Nemotron Nano 12B v2 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
15 OCT, 2025
Kind
Base model
Provider
NVIDIA
Huggingface
nvidia/NVIDIA-Nemotron-Nano-12B-v2

Specifications

Calibrated
No
Mixture-of-Experts
No
Parameters
12B

Supporting Functionality

Fine-tuning
Not Supported
Serverless
Not Supported
Context Length
128k tokens
Function Calling
Supported
Embeddings
Not Supported
Rerankers
Not Supported
Supporting image input
Not Supported