NE

NVIDIA Nemotron Labs 3 Elastic 12B A2B

NemotronGGUF by mradermacherUpdated 2026-05-11
Download on Hugging Face
Parameters12.4B
Context1024K
Layers52
Architecturenemotron_h_moe
Smallest quant0.0 GB
Quick answer

NVIDIA Nemotron Labs 3 Elastic 12B A2B needs about 17.1 GB of memory at Q4_K_M (a 9.6 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 25 quants, from 0.0 GB to 13.2 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 27.9 GB.

NVIDIA Nemotron Labs 3 Elastic 12B A2B – a 12.4B parameter reasoning model

The NVIDIA Nemotron Labs 3 Elastic 12B A2B is a 12.4B parameter model with 2B active experts. It supports up to 1,048,576 context tokens and is optimized for reasoning and tool use. The model is released under an other license and is available in multiple GGUF quantizations.

Good at

  • Reasoning
  • Tool use
  • Long‑context handling

Limits

  • No vision support
  • Requires large VRAM for full precision
  • License not open source

Best for

  • Complex reasoning tasks
  • Tool‑augmented workflows
  • Large‑context document analysis

Who it’s for. Developers and researchers who need a high‑capacity reasoning model for local deployment. The model is suitable for applications that require extended context and expert‑based inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 7.5 GB
Tight Get file →
IQ1_S7.1 GB 14.5 GB
Too big Get file →
IQ1_M7.1 GB 14.5 GB
Too big Get file →
IQ2_XXS7.1 GB 14.6 GB
Too big Get file →
IQ2_XS7.1 GB 14.6 GB
Too big Get file →
IQ2_S7.1 GB 14.6 GB
Too big Get file →
IQ2_M7.1 GB 14.6 GB
Too big Get file →
Q2_K7.1 GB 14.6 GB
Too big Get file →
IQ3_XXS7.1 GB 14.6 GB
Too big Get file →
IQ3_S7.1 GB 14.6 GB
Too big Get file →
IQ3_XS7.1 GB 14.6 GB
Too big Get file →
Q3_K_S7.1 GB 14.6 GB
Too big Get file →
IQ4_XS7.1 GB 14.6 GB
Too big Get file →
IQ4_NL7.1 GB 14.6 GB
Too big Get file →
Q2_K_S7.2 GB 14.6 GB
Too big Get file →
Q4_07.2 GB 14.7 GB
Too big Get file →
IQ3_M7.2 GB 14.7 GB
Too big Get file →
Q3_K_M7.8 GB 15.3 GB
Too big Get file →
Q4_17.9 GB 15.4 GB
Too big Get file →
Q3_K_L8.2 GB 15.7 GB
Too big Get file →
Q4_K_S8.7 GB 16.1 GB
Too big Get file →
Q5_K_S9.4 GB 16.9 GB
Too big Get file →
Q4_K_M9.6 GB 17.1 GB
Too big Get file →
Q5_K_M10.2 GB 17.7 GB
Too big Get file →
Q6_K13.2 GB 20.7 GB
Too big Get file →

For 8 GB VRAM, the IQ1_S or IQ1_M quant (7.07 GB file, ~14.5 GB RAM at 8 k context) is recommended. If 12 GB VRAM is available, IQ2_S or IQ2_M (7.08 GB file, ~14.6 GB RAM) provides a good balance of size and performance. For 16 GB VRAM, Q4_K_S (8.67 GB file, ~16.1 GB RAM) offers higher precision.

What GPU do you need for NVIDIA Nemotron Labs 3 Elastic 12B A2B?

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: the best quant that fits is the main file (0.0 GB file, about 7.5 GB in use).
  • 12 GB VRAM: the best quant that fits is the main file (0.0 GB file, about 7.5 GB in use).
  • 16 GB VRAM: the best quant that fits is Q3_K_L (8.2 GB file, about 15.7 GB in use).
  • 24 GB VRAM: the best quant that fits is Q6_K (13.2 GB file, about 20.7 GB in use).

Which NVIDIA Nemotron Labs 3 Elastic 12B A2B quant should you choose?

Q4_K_M is the usual starting point for NVIDIA Nemotron Labs 3 Elastic 12B A2B: it balances file size and quality well. Here it is a 9.6 GB file.

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_moe
Parameters12.4B (approximate, mixture of experts)
Active parameters2B
Layers52
Trained context1,048,576 tokens
KV cache (fp16)832 KB per token

Source

Quantized bymradermacher
FamilyNemotron
Licenseother
Downloads (HF)966
Last updated2026-05-11

Frequently asked questions about NVIDIA Nemotron Labs 3 Elastic 12B A2B

How much VRAM does NVIDIA Nemotron Labs 3 Elastic 12B A2B need?

About 17.1 GB at Q4_K_M with an 8K context window. That is the 9.6 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 NVIDIA Nemotron Labs 3 Elastic 12B A2B on an 8 GB GPU?

Yes, with the smaller files: the 0.0 GB file needs about 7.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of NVIDIA Nemotron Labs 3 Elastic 12B A2B GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 7.1 GB, IQ1_M is 7.1 GB, IQ2_XXS is 7.1 GB, IQ2_XS is 7.1 GB, IQ2_S is 7.1 GB and 19 more.

What context length does NVIDIA Nemotron Labs 3 Elastic 12B A2B 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 Labs 3 Elastic 12B A2B GGUF?

The files are on Hugging Face in the mradermacher/NVIDIA-Nemotron-Labs-3-Elastic-12B-A2B-i1-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 Labs 3 Elastic 12B A2B 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, using the IQ1_S or IQ1_M quant will fit within 8 GB VRAM, but RAM usage will be around 14.5 GB at 8 k context.

Does this model support vision?

No, the model has no vision capabilities.

What is the maximum context length?

The model supports up to 1,048,576 context tokens.

Other GGUFs of NVIDIA-Nemotron-Labs-3-Elastic-12B-A2B

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Nemotron models

All Nemotron →

Other medium models

All medium models →