Instructions to use mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF",
	filename="Nemotron-3-Super-120B-A12B-APEX-Balanced.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF
# Run inference directly in the terminal:
llama-cli -hf mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF
# Run inference directly in the terminal:
llama-cli -hf mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF
# Run inference directly in the terminal:
./llama-cli -hf mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF

Use Docker

docker model run hf.co/mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF

LM Studio
Jan
Ollama
How to use mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF with Ollama:
```
ollama run hf.co/mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF
```

Unsloth Studio

How to use mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF to start chatting

How to use mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF

Run Hermes

hermes

Docker Model Runner
How to use mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF with Docker Model Runner:
```
docker model run hf.co/mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF
```

Lemonade

How to use mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF

Run and chat with the model

lemonade run user.NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF-{{QUANT_TAG}}

List all available models

lemonade list

⚡ Each donation = another big MoE quantized

I host 25+ free APEX MoE quantizations as independent research. My only local hardware is an NVIDIA DGX Spark (122 GB unified memory) — enough for ~30-50B-class MoEs, but bigger ones (200B+) require rented compute on H100/H200/Blackwell, typically $20-100 per quant.
If APEX quants are useful to you, your support directly funds those bigger runs.

🎉 Patreon (Monthly) | ☕ Buy Me a Coffee | ⭐ GitHub Sponsors

💚 Big thanks to Hugging Face for generously donating additional storage — much appreciated.

Nemotron-3-Super-120B-A12B APEX GGUF

APEX (Adaptive Precision for EXpert Models) quantizations of NVIDIA-Nemotron-3-Super-120B-A12B.

Brought to you by the LocalAI team | APEX Project | Technical Report

Benchmark Results

Benchmarks coming soon. For reference APEX benchmarks on the Qwen3.5-35B-A3B architecture, see mudler/Qwen3.5-35B-A3B-APEX-GGUF.

What is APEX?

APEX is a quantization strategy for Mixture-of-Experts (MoE) models. It classifies tensors by role (routed expert, shared expert, attention) and applies a layer-wise precision gradient -- edge layers get higher precision, middle layers get more aggressive compression. I-variants use diverse imatrix calibration (chat, code, reasoning, tool-calling, agentic traces, Wikipedia).

See the APEX project for full details, technical report, and scripts.

Architecture

Model: NVIDIA-Nemotron-3-Super-120B-A12B (NemotronH)
Layers: 88
Type: Hybrid Mamba-2 / LatentMoE / Attention + Multi-Token Prediction (MTP)
Experts: 512 routed + 1 shared (22 active per token)
Total Parameters: 120B
Active Parameters: ~12B per token
APEX Config: 5+5 symmetric edge gradient across 88 layers

Run with LocalAI

local-ai run mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF@Nemotron-3-Super-120B-A12B-APEX-I-Balanced.gguf

Credits

APEX is brought to you by the LocalAI team. Developed through human-driven, AI-assisted research. Built on llama.cpp.

Downloads last month: 810

GGUF

Model size

121B params

Architecture

nemotron_h_moe

Hardware compatibility

We're not able to determine the quantization variants.

View all variants

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF

Base model

nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-BF16

Quantized

(43)

this model

Collection including mudler/NVIDIA-Nemotron-3-Super-120B-A12B-APEX-GGUF

APEX Quants (GGUF)

Collection

MoE models quantized with the APEX Quantization technique ( https://github.com/mudler/apex-quant ) • 36 items • Updated 8 days ago • 111