NE

NVIDIA-Nemotron-Nano-12B-v2

NemotronGGUF by MungertUpdated 2025-09-24
Download on Hugging Face
Parameters12.3B
Context1024K
Layers62
Architecturenemotron_h
Smallest quant0.0 GB
Quick answer

NVIDIA-Nemotron-Nano-12B-v2 needs about 18.9 GB of memory at Q4_K_M (a 7.9 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 28 quants, from 0.0 GB to 24.6 GB (BF16). Longer context needs more: at 32K tokens the KV cache alone adds about 41.6 GB.

NVIDIA‑Nemotron‑Nano‑12B‑v2‑GGUF – 12.3B hybrid LLM

NVIDIA‑Nemotron‑Nano‑12B‑v2‑GGUF is a 12.3B parameter hybrid Mamba‑Transformer model. It supports a 128K context length and is optimized for reasoning and tool use. The model is available in multiple quantizations for different memory budgets.

Good at

  • Reasoning
  • Tool integration
  • Large context handling

Limits

  • No vision support
  • License is other
  • No mixture of experts

Best for

  • Chatbot development
  • Code assistance
  • Research prototyping

Who it’s for. Developers and researchers building or deploying large language models. The model is ready for commercial use under NVIDIA Open Model License Agreement.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 10.9 GB
Too big Get file →
IQ1_S3.4 GB 14.3 GB
Too big Get file →
IQ1_M3.8 GB 14.7 GB
Too big Get file →
IQ2_XXS4.0 GB 14.9 GB
Too big Get file →
IQ2_XS4.4 GB 15.3 GB
Too big Get file →
IQ2_S4.5 GB 15.4 GB
Too big Get file →
Q2_K_S4.7 GB 15.6 GB
Too big Get file →
IQ2_M4.7 GB 15.6 GB
Too big Get file →
Q2_K_M4.8 GB 15.7 GB
Too big Get file →
IQ3_XXS5.5 GB 16.4 GB
Too big Get file →
IQ3_XS5.8 GB 16.7 GB
Too big Get file →
Q3_K_S6.1 GB 17.0 GB
Too big Get file →
IQ3_M6.2 GB 17.1 GB
Too big Get file →
Q3_K_M6.2 GB 17.1 GB
Too big Get file →
IQ4_NL6.9 GB 17.8 GB
Too big Get file →
IQ4_XS6.9 GB 17.8 GB
Too big Get file →
Q4_K_S7.4 GB 18.3 GB
Too big Get file →
Q4_07.6 GB 18.5 GB
Too big Get file →
Q4_17.8 GB 18.7 GB
Too big Get file →
Q4_K_M7.9 GB 18.9 GB
Too big Get file →
Q5_09.0 GB 19.9 GB
Too big Get file →
Q5_K_M9.2 GB 20.1 GB
Too big Get file →
Q5_19.7 GB 20.6 GB
Too big Get file →
Q6_K_M10.4 GB 21.3 GB
Too big Get file →
Q8_013.1 GB 24.0 GB
Too big Get file →
BF1617.3 GB 28.2 GB
Too big Get file →
F1617.3 GB 28.2 GB
Too big Get file →
BF1624.6 GB 35.5 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (file size 3.4 GB, estimated 14.3 GB memory). For 12 GB VRAM, use Q4_K_M (file size 7.95 GB, estimated 18.9 GB memory). For 24 GB VRAM, use Q8_0 (file size 13.09 GB, estimated 24 GB memory).

What GPU do you need for NVIDIA-Nemotron-Nano-12B-v2?

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 the main file (0.0 GB file, about 10.9 GB in use).
  • 16 GB VRAM: the best quant that fits is Q2_K_M (4.8 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q8_0 (13.1 GB file, about 24.0 GB in use).
  • 32 GB VRAM: the best quant that fits is BF16 (17.3 GB file, about 28.2 GB in use).
  • 48 GB VRAM: the best quant that fits is BF16 (24.6 GB file, about 35.5 GB in use).

Which NVIDIA-Nemotron-Nano-12B-v2 quant should you choose?

Q4_K_M is the usual starting point for NVIDIA-Nemotron-Nano-12B-v2: it balances file size and quality well. Here it is a 7.9 GB file.

The Q8_0 file is 13.1 GB, about 1.6 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 the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturenemotron_h
Parameters12.3B
Layers62
Trained context1,048,576 tokens
KV cache (fp16)1240 KB per token

Source

Quantized byMungert
FamilyNemotron
Licenseother
Downloads (HF)672
Last updated2025-09-24

Frequently asked questions about NVIDIA-Nemotron-Nano-12B-v2

How much VRAM does NVIDIA-Nemotron-Nano-12B-v2 need?

About 18.9 GB at Q4_K_M with an 8K context window. That is the 7.9 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-Nano-12B-v2 on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.9 GB, so you would need a larger GPU or CPU offloading.

What is the file size of NVIDIA-Nemotron-Nano-12B-v2 GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 3.4 GB, IQ1_M is 3.8 GB, IQ2_XXS is 4.0 GB, IQ2_XS is 4.4 GB, IQ2_S is 4.5 GB and 22 more.

What context length does NVIDIA-Nemotron-Nano-12B-v2 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 10.4 GB at 8K and 41.6 GB at 32K.

Where can I download NVIDIA-Nemotron-Nano-12B-v2 GGUF?

The files are on Hugging Face in the Mungert/NVIDIA-Nemotron-Nano-12B-v2-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-Nano-12B-v2 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 IQ1_S quantization requires about 14.3 GB memory at 8 k context, which fits an 8 GB VRAM setup with some overhead.

Does the model support image inputs?

No, the model does not include vision capabilities.

What is the maximum context length?

The model supports a context length of 128K tokens.

Other GGUFs of NVIDIA-Nemotron-Nano-12B-v2-Base

Similar models

Browse all →

More from Mungert

All by Mungert →

More Nemotron models

All Nemotron →

Other medium models

All medium models →