NE

Nemotron 3 Super 120B A12B

NemotronGGUF by lmstudio-communityUpdated 2026-03-11
Download on Hugging Face
Parameters121B
Context1024K
Layers88
Architecturenemotron_h_moe
Smallest quant86.1 GB
Quick answer

Nemotron 3 Super 120B A12B needs about 98.4 GB of memory at Q4_K_M (a 86.1 GB file) with an 8K context window, which is more than a 48 GB GPU holds. This repository has 3 quants, from 86.1 GB (Q4_K_M) to 128.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 47.2 GB.

Nemotron 3 Super 120B A12B – 120B parameter LLM with 12B active experts

Nemotron 3 Super 120B A12B is a large language model from NVIDIA. It uses a latent mixture‑of‑experts architecture with 12B active parameters out of 120B total. The model supports up to 1,048,576 context tokens and is available in GGUF format.

Good at

  • Strong agentic reasoning
  • High‑volume IT ticket automation
  • Multi‑token generation

Limits

  • Requires large VRAM (≈140 GB for Q8_0 at 8 k context)
  • No vision support
  • License governed by NVIDIA Nemotron Open Model License

Best for

  • Deploying collaborative AI agents
  • Automating technical support workflows
  • Generating long‑form reasoning traces

Who it’s for. Developers building agentic or reasoning‑heavy applications who need a large, efficient model. The model is ready for commercial use and supports multiple languages including English, French, German, Italian, Japanese, Spanish, and Chinese.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M86.1 GB (3 parts) 98.4 GB
Too big Get file →
Q6_K112.9 GB (3 parts) 125.2 GB
Too big Get file →
Q8_0128.5 GB (4 parts) 140.8 GB
Too big Get file →

For 8 GB VRAM use Q4_K_M (86 GB file, ~98 GB memory at 8 k context). With 16 GB VRAM Q6_K is feasible (112 GB file, ~125 GB memory). For 32 GB VRAM Q8_0 provides the highest quality (128 GB file, ~141 GB memory).

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

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: no quant fits at an 8K context.
  • 48 GB VRAM: no quant fits at an 8K context.

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

Q4_K_M is the usual starting point for Nemotron 3 Super 120B A12B: it balances file size and quality well. Here it is a 86.1 GB file.

The Q8_0 file is 128.5 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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturenemotron_h_moe
Parameters121B (approximate, mixture of experts)
Active parameters12B
Layers88
Trained context1,048,576 tokens
KV cache (fp16)1408 KB per token

Source

Quantized bylmstudio-community
FamilyNemotron
Licenseother
Downloads (HF)3,827
Last updated2026-03-11

Frequently asked questions about Nemotron 3 Super 120B A12B

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

About 98.4 GB at Q4_K_M with an 8K context window. That is the 86.1 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 Super 120B A12B on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 98.4 GB, so you would need a larger GPU or CPU offloading.

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

It depends on the quant: Q4_K_M is 86.1 GB, Q6_K is 112.9 GB, Q8_0 is 128.5 GB.

What context length does Nemotron 3 Super 120B A12B 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 11.8 GB at 8K and 47.2 GB at 32K.

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

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

No, the smallest quant requires about 98 GB of VRAM at 8 k context. 8 GB VRAM is insufficient.

Does the model support image inputs?

No, the model has no vision capability.

What is the maximum context length?

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

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

Similar models

Browse all →

More from lmstudio-community

All by lmstudio-community →

More Nemotron models

All Nemotron →

Other large models

All large models →