NE

Nemotron-3-Nano-30B-A3B

NemotronGGUF by unslothUpdated 2025-12-31
Download on Hugging Face
Parameters31.6B
Context1024K
Layers52
Architecturenemotron_h_moe
Smallest quant18.1 GB
Quick answer

Nemotron-3-Nano-30B-A3B needs about 32.1 GB of memory at Q4_K_M (a 24.6 GB file) with an 8K context window, so it fits on a 48 GB GPU. This repository has 23 quants, from 18.1 GB (Q2_K_L) to 63.2 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 27.9 GB.

30B‑parameter Nemotron model with MoE, optimized for coding tasks

Nemotron‑3‑Nano‑30B‑A3B is a 30 B parameter LLM with a hybrid Mixture‑of‑Experts architecture. It supports up to 1 048 576 context tokens and is tuned for coding. The model is released under the NVIDIA Nemotron Open Model License.

Good at

  • Large context reasoning
  • Efficient coding generation
  • Hybrid MoE architecture

Limits

  • Requires high VRAM for large contexts
  • No vision support
  • License is NVIDIA Nemotron Open Model License

Best for

  • Developers building code assistants
  • Researchers testing MoE models
  • Applications needing long‑context reasoning

Who it’s for. Engineers and researchers who need a large, MoE‑based language model for coding and long‑context tasks. The model is suitable for those who can allocate sufficient GPU memory and comply with the NVIDIA license.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q2_K_L18.1 GB 25.6 GB
Too big Get file →
IQ2_XXS18.1 GB 25.6 GB
Too big Get file →
Q3_K_S18.1 GB 25.6 GB
Too big Get file →
IQ2_M18.1 GB 25.6 GB
Too big Get file →
IQ3_XXS18.1 GB 25.6 GB
Too big Get file →
IQ4_XS18.2 GB 25.6 GB
Too big Get file →
IQ4_NL18.2 GB 25.7 GB
Too big Get file →
Q4_018.2 GB 25.7 GB
Too big Get file →
Q2_K_XL19.9 GB 27.4 GB
Too big Get file →
Q3_K_XL19.9 GB 27.4 GB
Too big Get file →
Q3_K_M20.0 GB 27.5 GB
Too big Get file →
Q4_120.1 GB 27.5 GB
Too big Get file →
Q4_K_S22.0 GB 29.5 GB
Too big Get file →
Q4_K_XL22.8 GB 30.3 GB
Too big Get file →
Q5_K_S24.0 GB 31.4 GB
Too big Get file →
Q4_K_M24.6 GB 32.1 GB
Too big Get file →
Q5_K_M26.1 GB 33.6 GB
Too big Get file →
Q5_K_XL27.5 GB 35.0 GB
Too big Get file →
Q6_K33.5 GB 41.0 GB
Too big Get file →
Q6_K_XL33.5 GB 41.0 GB
Too big Get file →
Q8_033.6 GB 41.1 GB
Too big Get file →
Q8_K_XL40.4 GB 47.9 GB
Too big Get file →
BF1663.2 GB (2 parts) 70.7 GB
Too big Get file →

For 8 GB VRAM, use Q2_K_L or IQ2_XXS (≈18 GB file, 25.6 GB memory at 8 k context). For 16 GB VRAM, Q4_0 or Q4_1 (≈20 GB file, 27.5 GB memory). For 24 GB VRAM, Q4_K_M (≈24.6 GB file, 32.1 GB memory).

What GPU do you need for 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 Q5_K_S (24.0 GB file, about 31.4 GB in use).
  • 48 GB VRAM: the best quant that fits is Q8_K_XL (40.4 GB file, about 47.9 GB in use).

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

Q4_K_M is the usual starting point for Nemotron-3-Nano-30B-A3B: it balances file size and quality well. Here it is a 24.6 GB file.

The Q8_0 file is 33.6 GB, about 1.4 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 Q2_K_L at 18.1 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_moe
Parameters31.6B (approximate, mixture of experts)
Active parameters3B
Layers52
Trained context1,048,576 tokens
KV cache (fp16)832 KB per token

Source

Quantized byunsloth
FamilyNemotron
Licenseother
Downloads (HF)39,483
Last updated2025-12-31

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

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

About 32.1 GB at Q4_K_M with an 8K context window. That is the 24.6 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 Nemotron-3-Nano-30B-A3B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 25.6 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: Q2_K_L is 18.1 GB, IQ2_XXS is 18.1 GB, Q3_K_S is 18.1 GB, IQ2_M is 18.1 GB, IQ3_XXS is 18.1 GB, IQ4_XS is 18.2 GB and 17 more.

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

The files are on Hugging Face in the unsloth/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 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 Nemotron‑3‑Nano‑30B‑A3B on 8 GB VRAM?

Only the smallest quantizations such as Q2_K_L or IQ2_XXS can be loaded, but they still require about 25.6 GB of VRAM at 8 k context, so 8 GB is insufficient.

Does the model support image inputs?

No, the model has no vision capabilities.

What license applies to this model?

It is governed by the NVIDIA Nemotron Open Model License.

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

Similar models

Browse all →

More from unsloth

All by unsloth →

More Nemotron models

All Nemotron →

Other medium models

All medium models →