NE

Nemotron 3 Nano Omni 30B A3B Reasoning APEX

NemotronGGUF by mudlerUpdated 2026-08-17
Download on Hugging Face
Parameters31.6B
Context1024K
Layers52
Architecturenemotron_h_moe
Smallest quant18.0 GB
Quick answer

Nemotron 3 Nano Omni 30B A3B Reasoning APEX needs about 30.5 GB of memory at its main file (a 23.0 GB file) with an 8K context window, so it fits on a 32 GB GPU. This repository has 9 quants, from 18.0 GB to 63.2 GB (F16). Longer context needs more: at 32K tokens the KV cache alone adds about 27.9 GB.

Nemotron 3 Nano Omni 30B A3B Reasoning APEX – multimodal LLM with MoE

Nemotron 3 Nano Omni 30B A3B Reasoning APEX is a multimodal large language model that supports video, audio, image, and text inputs. It uses a Mamba2‑Transformer hybrid mixture of experts with 32 billion parameters and 3 billion active parameters per token. The model is available in GGUF format and can be run with llama.cpp.

Good at

  • Video and audio understanding
  • OCR and transcription
  • Enterprise document intelligence

Limits

  • Requires large VRAM (≈70 GB for F16 quant at 8k context)
  • No vision support in non‑MoE quantizations
  • License governed by NVIDIA Open Model Agreement

Best for

  • Enterprise Q&A on video content
  • M&E asset summarization
  • Document‑centric AI assistants

Who it’s for. Enterprise users needing robust multimodal reasoning. Ideal for customer service, media analysis, and document intelligence workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—18.0 GB 25.5 GB
Too big Get file →
—18.8 GB 26.2 GB
Too big Get file →
—20.3 GB 27.8 GB
Too big Get file →
—20.3 GB 27.8 GB
Too big Get file →
—23.0 GB 30.5 GB
Too big Get file →
—23.0 GB 30.5 GB
Too big Get file →
—27.2 GB 34.7 GB
Too big Get file →
—27.2 GB 34.7 GB
Too big Get file →
F1663.2 GB 70.7 GB
Too big Get file →

For 8 GB VRAM use the smallest available quant (unknown quant, 18 GB file, ~25.5 GB memory at 8k context). For 16 GB VRAM use the 18.77 GB file (~26.2 GB memory). For 32 GB VRAM use the 20.34 GB file (~27.8 GB memory). The F16 quant requires ~63 GB file and ~70.7 GB memory, suitable only for high‑end GPUs.

What GPU do you need for Nemotron 3 Nano Omni 30B A3B Reasoning APEX?

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 the main file (23.0 GB file, about 30.5 GB in use).
  • 48 GB VRAM: the best quant that fits is the main file (27.2 GB file, about 34.7 GB in use).

Which Nemotron 3 Nano Omni 30B A3B Reasoning APEX quant should you choose?

If memory is tight, the smallest file is the first one in the table at 18.0 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
Parameters31.6B (approximate, mixture of experts)
Active parameters3B
Layers52
Trained context1,048,576 tokens
KV cache (fp16)832 KB per token

Source

Quantized bymudler
FamilyNemotron
Licenseother
Downloads (HF)10,028
Last updated2026-08-17

Frequently asked questions about Nemotron 3 Nano Omni 30B A3B Reasoning APEX

How much VRAM does Nemotron 3 Nano Omni 30B A3B Reasoning APEX need?

About 30.5 GB at its main file with an 8K context window. That is the 23.0 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 Omni 30B A3B Reasoning APEX on an 8 GB GPU?

Not at an 8K context. The smallest file needs about 25.5 GB, so you would need a larger GPU or CPU offloading.

What is the file size of Nemotron 3 Nano Omni 30B A3B Reasoning APEX GGUF?

It depends on the quant: file is 18.0 GB, file is 18.8 GB, file is 20.3 GB, file is 20.3 GB, file is 23.0 GB, file is 23.0 GB and 3 more.

What context length does Nemotron 3 Nano Omni 30B A3B Reasoning APEX 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 Omni 30B A3B Reasoning APEX GGUF?

The files are on Hugging Face in the mudler/Nemotron-3-Nano-Omni-30B-A3B-Reasoning-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 Nemotron 3 Nano Omni 30B A3B Reasoning 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 8 GB VRAM?

No, the smallest quant requires about 25.5 GB memory at 8k context, which exceeds 8 GB VRAM.

Does the model support vision?

Yes, the model includes vision encoders for image and video frames.

What license applies?

Use is governed by the NVIDIA Open Model Agreement.

Other GGUFs of Nemotron-3-Nano-Omni-30B-A3B-Reasoning-BF16

Similar models

Browse all →

More from mudler

All by mudler →

More Nemotron models

All Nemotron →

Other medium models

All medium models →