llama
8B parameters
Commercial OK

Llama 3.1 Nemotron Nano 8B

Smallest of the Nemotron reasoning trio. NAS-optimized for inference efficiency on RTX hardware.

License: Llama 3.1 Community License·Released Apr 8, 2025·Context: 131,072 tokens

Overview

Smallest of the Nemotron reasoning trio. NAS-optimized for inference efficiency on RTX hardware.

Strengths

  • RTX-optimized
  • Reasoning at 8B

Weaknesses

  • NVIDIA license terms

Quantization variants

Each quantization trades model quality for file size and VRAM. Q4_K_M is the most popular starting point.

QuantizationFile sizeVRAM required
Q4_K_M4.9 GB6 GB

Get the model

HuggingFace

Original weights

huggingface.co/nvidia/Llama-3.1-Nemotron-Nano-8B-v1

Source repository — direct quantization required.

Hardware that runs this

Cards with enough VRAM for at least one quantization of Llama 3.1 Nemotron Nano 8B.

Compare alternatives

Models worth comparing

Same parameter band, plus what's one tier above and below — so you can decide what actually fits your hardware.

Frequently asked

What's the minimum VRAM to run Llama 3.1 Nemotron Nano 8B?

6GB of VRAM is enough to run Llama 3.1 Nemotron Nano 8B at the Q4_K_M quantization (file size 4.9 GB). Higher-quality quantizations need more.

Can I use Llama 3.1 Nemotron Nano 8B commercially?

Yes — Llama 3.1 Nemotron Nano 8B ships under the Llama 3.1 Community License, which permits commercial use. Always read the license text before deployment.

What's the context length of Llama 3.1 Nemotron Nano 8B?

Llama 3.1 Nemotron Nano 8B supports a context window of 131,072 tokens (about 131K).

Source: huggingface.co/nvidia/Llama-3.1-Nemotron-Nano-8B-v1

Reviewed by RunLocalAI Editorial. See our editorial policy for how we research and verify model claims.