NE

Nvidia-Nemotron-3-Nano-4B

NemotronGGUF by unslothUpdated 2026-03-17
Download on Hugging Face
Parameters3.97B
Context1024K
Layers42
Architecturenemotron_h
Smallest quant2.2 GB
Quick answer

Nvidia-Nemotron-3-Nano-4B needs about 10.4 GB of memory at Q4_K_M (a 2.9 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 22 quants, from 2.2 GB (IQ2_XXS) to 8.0 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 28.2 GB.

Nvidia-Nemotron-3-Nano-4B: 4B parameter edge‑ready LLM

Nvidia-Nemotron-3-Nano-4B is a 4 billion parameter small language model designed for edge platforms. It uses a hybrid nemotron_h architecture with Mamba‑2, MLP and four attention layers. The model supports reasoning and non‑reasoning tasks and is available in multiple GGUF quantizations.

Good at

  • Reasoning with optional trace
  • Low‑latency inference on edge GPUs
  • Compact 4 B parameter size

Limits

  • Requires 8 k context for full memory estimates
  • No vision or multimodal support
  • License governed by NVIDIA Nemotron Open Model License

Best for

  • Local voice assistants
  • Game NPC dialogue
  • IoT automation scripts

Who it’s for. Developers building agentic AI on Jetson, GeForce RTX or DGX Spark. The model is suitable for applications needing quick, on‑device language understanding and generation in English and coding languages.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_XXS2.2 GB 9.7 GB
Too big Get file →
IQ2_M2.3 GB 9.8 GB
Too big Get file →
Q3_K_S2.4 GB 9.9 GB
Too big Get file →
IQ3_XXS2.4 GB 9.9 GB
Too big Get file →
Q3_K_M2.5 GB 10.0 GB
Too big Get file →
Q2_K_XL2.5 GB 10.1 GB
Too big Get file →
Q4_02.5 GB 10.1 GB
Too big Get file →
IQ4_XS2.5 GB 10.1 GB
Too big Get file →
IQ4_NL2.6 GB 10.1 GB
Too big Get file →
Q3_K_XL2.7 GB 10.2 GB
Too big Get file →
Q4_12.7 GB 10.3 GB
Too big Get file →
Q4_K_S2.8 GB 10.4 GB
Too big Get file →
Q4_K_M2.9 GB 10.4 GB
Too big Get file →
Q5_K_S3.1 GB 10.7 GB
Too big Get file →
Q4_K_XL3.1 GB 10.7 GB
Too big Get file →
Q5_K_M3.2 GB 10.7 GB
Too big Get file →
Q5_K_XL3.3 GB 10.9 GB
Too big Get file →
Q6_K4.1 GB 11.6 GB
Too big Get file →
Q8_04.2 GB 11.8 GB
Too big Get file →
Q6_K_XL4.6 GB 12.1 GB
Too big Get file →
Q8_K_XL5.6 GB 13.2 GB
Too big Get file →
BF168.0 GB 15.5 GB
Too big Get file →

For 8 GB VRAM, use Q4_0 or Q4_1 (≈10 GB memory at 8 k context). With 12 GB VRAM, Q6_K_XL or Q8_K_XL provide higher quality. For 16 GB VRAM, BF16 offers the best fidelity but needs 15.5 GB memory.

What GPU do you need for Nvidia-Nemotron-3-Nano-4B?

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: the best quant that fits is Q8_0 (4.2 GB file, about 11.8 GB in use).
  • 16 GB VRAM: the best quant that fits is BF16 (8.0 GB file, about 15.5 GB in use).

Which Nvidia-Nemotron-3-Nano-4B quant should you choose?

Q4_K_M is the usual starting point for Nvidia-Nemotron-3-Nano-4B: it balances file size and quality well. Here it is a 2.9 GB file.

The Q8_0 file is 4.2 GB, about 1.5 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ2_XXS at 2.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturenemotron_h
Parameters3.97B
Layers42
Trained context1,048,576 tokens
KV cache (fp16)840 KB per token

Source

Quantized byunsloth
FamilyNemotron
Licenseother
Downloads (HF)9,036
Last updated2026-03-17

Frequently asked questions about Nvidia-Nemotron-3-Nano-4B

How much VRAM does Nvidia-Nemotron-3-Nano-4B need?

About 10.4 GB at Q4_K_M with an 8K context window. That is the 2.9 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-4B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 9.7 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Nvidia-Nemotron-3-Nano-4B GGUF?

It depends on the quant: IQ2_XXS is 2.2 GB, IQ2_M is 2.3 GB, Q3_K_S is 2.4 GB, IQ3_XXS is 2.4 GB, Q3_K_M is 2.5 GB, Q2_K_XL is 2.5 GB and 16 more.

What context length does Nvidia-Nemotron-3-Nano-4B 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 28.2 GB at 32K.

Where can I download Nvidia-Nemotron-3-Nano-4B GGUF?

The files are on Hugging Face in the unsloth/NVIDIA-Nemotron-3-Nano-4B-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-4B 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 Nvidia‑Nemotron‑3‑Nano‑4B on 8 GB VRAM?

Yes, with Q4_0 or Q4_1 quantization the model uses about 10 GB memory at 8 k context, which fits 8 GB VRAM with some headroom.

Does the model support vision tasks?

No, the model only supports text and coding languages.

What is the maximum context length?

The model was trained with 1,048,576 tokens and supports up to that context length.

Other GGUFs of NVIDIA-Nemotron-3-Nano-4B-BF16

Similar models

Browse all →

More from unsloth

All by unsloth →

More Nemotron models

All Nemotron →

Other small models

All small models →