NE

NVIDIA Nemotron 3 Super 120B A12B APEX

NemotronGGUF by mudlerUpdated 2026-08-17
Download on Hugging Face
Parameters121B
Context—
Layers—
Architecture—
Smallest quant8.9 GB
Quick answer

NVIDIA Nemotron 3 Super 120B A12B APEX needs about 86.0 GB of memory at its main file (a 76.4 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 7 quants, from 8.9 GB to 97.5 GB.

NVIDIA Nemotron 3 Super 120B A12B APEX – large LLM with 120B parameters and 12B active per token

NVIDIA Nemotron 3 Super 120B A12B APEX is a 120B parameter LLM optimized for agentic, reasoning, and conversational tasks. It uses a hybrid Mamba‑2 / LatentMoE architecture with Multi‑Token Prediction layers. The model is ready for commercial use.

Good at

  • Agentic reasoning
  • High‑volume IT ticket automation
  • Collaborative agent tasks

Limits

  • Requires large VRAM – 10.5GB minimum at 8k context
  • No vision support
  • License governed by NVIDIA Nemotron Open Model License

Best for

  • Building specialized AI agents
  • Automating IT support workflows
  • Deploying high‑volume conversational services

Who it’s for. Developers and enterprises needing a powerful, agent‑ready LLM for large‑scale conversational or reasoning workloads. The model is suitable for commercial deployment and supports multiple languages including English, French, German, Italian, Japanese, Spanish, and Chinese.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—8.9 GB 10.5 GB
Too big Get file →
—65.7 GB 74.1 GB
Too big Get file →
—65.7 GB 74.1 GB
Too big Get file →
—76.4 GB 86.0 GB
Too big Get file →
—76.4 GB 86.0 GB
Too big Get file →
—97.5 GB 109.7 GB
Too big Get file →
—97.5 GB 109.7 GB
Too big Get file →

For 12GB VRAM, use the 8.9GB file (est. 10.5GB memory at 8k context). For 16GB VRAM, the 65.75GB file (est. 74.1GB memory) is appropriate. For 24GB VRAM, the 76.37GB file (est. 86GB memory) fits. Memory estimates are approximate.

What GPU do you need for NVIDIA Nemotron 3 Super 120B A12B APEX?

These figures add the file size, an fp16 KV cache at an 8K context window 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 (8.9 GB file, about 10.5 GB in use).
  • 16 GB VRAM: the best quant that fits is the main file (8.9 GB file, about 10.5 GB in use).
  • 24 GB VRAM: the best quant that fits is the main file (8.9 GB file, about 10.5 GB in use).
  • 32 GB VRAM: the best quant that fits is the main file (8.9 GB file, about 10.5 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (8.9 GB file, about 10.5 GB in use).

Which NVIDIA Nemotron 3 Super 120B A12B APEX quant should you choose?

If memory is tight, the smallest file is the first one in the table at 8.9 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

Parameters121B

Source

Quantized bymudler
FamilyNemotron
Licenseother
Downloads (HF)2,892
Last updated2026-08-17

Frequently asked questions about NVIDIA Nemotron 3 Super 120B A12B APEX

How much VRAM does NVIDIA Nemotron 3 Super 120B A12B APEX need?

About 86.0 GB at its main file with an 8K context window. That is the 76.4 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 Super 120B A12B APEX on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 10.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of NVIDIA Nemotron 3 Super 120B A12B APEX GGUF?

It depends on the quant: file is 8.9 GB, file is 65.7 GB, file is 65.7 GB, file is 76.4 GB, file is 76.4 GB, file is 97.5 GB and 1 more.

Where can I download NVIDIA Nemotron 3 Super 120B A12B APEX GGUF?

The files are on Hugging Face in the mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-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 Super 120B A12B APEX 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 8GB VRAM?

No. The smallest file requires 10.5GB of VRAM at 8k context, so 8GB is insufficient.

Does the model support vision?

No. The model has no vision capabilities.

Is the model ready for commercial use?

Yes. The model is ready for commercial deployment under the NVIDIA Nemotron Open Model License.

Other GGUFs of NVIDIA-Nemotron-3-Super-120B-A12B-BF16

Similar models

Browse all →

More from mudler

All by mudler →

More Nemotron models

All Nemotron →

Other large models

All large models →