NE

NVIDIA-Nemotron-3-Nano-30B-A3B

NemotronGGUF by vultrUpdated 2026-10-20
Download on Hugging Face
Parameters31.6B
Context1024K
Layers52
Architecturenemotron_h_moe
Smallest quant19.7 GB
Quick answer

NVIDIA-Nemotron-3-Nano-30B-A3B needs about 34.4 GB of memory at Q4_K_M (a 27.0 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 4 quants, from 19.7 GB (IQ3_S) to 28.6 GB (Q5_K_M). Longer context needs more: at 32K tokens the KV cache alone adds about 27.9 GB.

NVIDIA Nemotron 3 Nano 30B A3B – a hybrid MoE LLM for reasoning and general tasks

NVIDIA Nemotron 3 Nano 30B A3B is a 30B parameter large language model with 3.5B active parameters. It uses a hybrid Mixture-of-Experts architecture and supports reasoning and tool use. The model is available in several GGUF quantizations.

Good at

  • Reasoning tasks
  • Tool integration
  • Configurable reasoning traces

Limits

  • Large context length requires high VRAM
  • No vision support
  • License type is other

Best for

  • AI agents needing reasoning
  • Customizable chat workflows
  • Commercial deployments

Who it’s for. Developers building AI agents that require reasoning and tool use. The model is suitable for applications where configurable reasoning traces improve solution quality.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ3_S19.7 GB 27.2 GB
Too big Get file →
IQ3_M19.9 GB 27.4 GB
Too big Get file →
Q4_K_M27.0 GB 34.4 GB
Too big Get file →
Q5_K_M28.6 GB 36.1 GB
Too big Get file →

For 8 GB VRAM use IQ3_S (19.72 GB file, 27.2 GB memory at 8 k context). For 12 GB VRAM use IQ3_M (19.91 GB file, 27.4 GB memory). For 16 GB VRAM use Q4_K_M (26.96 GB file, 34.4 GB memory). Memory estimates are approximate.

What GPU do you need for NVIDIA-Nemotron-3-Nano-30B-A3B?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: no quant fits at an 8K context.
  • 6 GB VRAM: no quant fits at an 8K context.
  • 8 GB VRAM: no quant fits at an 8K context.
  • 12 GB VRAM: no quant fits at an 8K context.
  • 16 GB VRAM: no quant fits at an 8K context.
  • 24 GB VRAM: no quant fits at an 8K context.
  • 32 GB VRAM: the best quant that fits is IQ3_M (19.9 GB file, about 27.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q5_K_M (28.6 GB file, about 36.1 GB in use).

Which NVIDIA-Nemotron-3-Nano-30B-A3B quant should you choose?

Q4_K_M is the usual starting point for NVIDIA-Nemotron-3-Nano-30B-A3B: it balances file size and quality well. Here it is a 27.0 GB file.

If memory is tight, the smallest file is IQ3_S at 19.7 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturenemotron_h_moe
Parameters31.6B (approximate, mixture of experts)
Active parameters3B
Layers52
Trained context1,048,576 tokens
KV cache (fp16)832 KB per token

Source

Quantized byvultr
FamilyNemotron
Licenseother
Downloads (HF)4,442
Last updated2026-10-20

Frequently asked questions about NVIDIA-Nemotron-3-Nano-30B-A3B

How much VRAM does NVIDIA-Nemotron-3-Nano-30B-A3B need?

About 34.4 GB at Q4_K_M with an 8K context window. That is the 27.0 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run NVIDIA-Nemotron-3-Nano-30B-A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 27.2 GB, so you would need a larger GPU or CPU offloading.

What is the file size of NVIDIA-Nemotron-3-Nano-30B-A3B GGUF?

It depends on the quant: IQ3_S is 19.7 GB, IQ3_M is 19.9 GB, Q4_K_M is 27.0 GB, Q5_K_M is 28.6 GB.

What context length does NVIDIA-Nemotron-3-Nano-30B-A3B support?

The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 7.0 GB at 8K and 27.9 GB at 32K.

Where can I download NVIDIA-Nemotron-3-Nano-30B-A3B GGUF?

The files are on Hugging Face in the vultr/NVIDIA-Nemotron-3-Nano-30B-A3B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does NVIDIA-Nemotron-3-Nano-30B-A3B use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, the IQ3_S quantization requires about 27.2 GB memory at 8 k context, which fits in 8 GB VRAM with efficient batching.

Does the model support vision?

No, the model does not have vision capabilities.

What is the context length?

The model was trained with a context length of 1,048,576 tokens.

Other GGUFs of NVIDIA-Nemotron-3-Nano-30B-A3B-BF16

Similar models

Browse all →

More from vultr

All by vultr →

More Nemotron models

All Nemotron →

Other medium models

All medium models →