Instructions to use hendrik289/Nex-N2-mini-Q8_0-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hendrik289/Nex-N2-mini-Q8_0-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="hendrik289/Nex-N2-mini-Q8_0-GGUF",
	filename="Nex-N2-mini-Q8_0.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use hendrik289/Nex-N2-mini-Q8_0-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf hendrik289/Nex-N2-mini-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf hendrik289/Nex-N2-mini-Q8_0-GGUF:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf hendrik289/Nex-N2-mini-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
llama-cli -hf hendrik289/Nex-N2-mini-Q8_0-GGUF:Q8_0

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 hendrik289/Nex-N2-mini-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf hendrik289/Nex-N2-mini-Q8_0-GGUF:Q8_0

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 hendrik289/Nex-N2-mini-Q8_0-GGUF:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf hendrik289/Nex-N2-mini-Q8_0-GGUF:Q8_0

Use Docker

docker model run hf.co/hendrik289/Nex-N2-mini-Q8_0-GGUF:Q8_0

LM Studio
Jan

vLLM

How to use hendrik289/Nex-N2-mini-Q8_0-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hendrik289/Nex-N2-mini-Q8_0-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hendrik289/Nex-N2-mini-Q8_0-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hendrik289/Nex-N2-mini-Q8_0-GGUF:Q8_0

Ollama
How to use hendrik289/Nex-N2-mini-Q8_0-GGUF with Ollama:
```
ollama run hf.co/hendrik289/Nex-N2-mini-Q8_0-GGUF:Q8_0
```

Unsloth Studio

How to use hendrik289/Nex-N2-mini-Q8_0-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 hendrik289/Nex-N2-mini-Q8_0-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 hendrik289/Nex-N2-mini-Q8_0-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for hendrik289/Nex-N2-mini-Q8_0-GGUF to start chatting

How to use hendrik289/Nex-N2-mini-Q8_0-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf hendrik289/Nex-N2-mini-Q8_0-GGUF:Q8_0

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": "hendrik289/Nex-N2-mini-Q8_0-GGUF:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use hendrik289/Nex-N2-mini-Q8_0-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 hendrik289/Nex-N2-mini-Q8_0-GGUF:Q8_0

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 hendrik289/Nex-N2-mini-Q8_0-GGUF:Q8_0

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use hendrik289/Nex-N2-mini-Q8_0-GGUF with Docker Model Runner:
```
docker model run hf.co/hendrik289/Nex-N2-mini-Q8_0-GGUF:Q8_0
```

Lemonade

How to use hendrik289/Nex-N2-mini-Q8_0-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull hendrik289/Nex-N2-mini-Q8_0-GGUF:Q8_0

Run and chat with the model

lemonade run user.Nex-N2-mini-Q8_0-GGUF-Q8_0

List all available models

lemonade list

Nex-N2-mini Q8_0 GGUF

Quantized GGUF version of nex-agi/Nex-N2-mini — an agentic model with Agentic Thinking, built on Qwen3.5-35B-A3B-Base.

⚠️ Disclaimer

This is my first time uploading a quantized model to Hugging Face. I am not affiliated with nex-agi. This is a community contribution — use at your own discretion.

I have modified the chat template so that reasoning (thinking) works correctly with llama.cpp. Without this adjustment, the reasoning output was not properly separated from the response. If you encounter any issues, please open a discussion.

Available Quantization

File	Quant	Size
`Nex-N2-mini-Q8_0.gguf`	Q8_0	~35 GB

Usage with llama.cpp

Recommended Start Parameters

./llama-server \
  --model Nex-N2-mini-Q8_0.gguf \
  --jinja \
  --reasoning on \
  --reasoning-format deepseek-legacy \
  --temp 0.7 \
  --top-p 0.95 \
  --top-k 40 \
  -ngl 99

Key Flags Explained

Flag	Value	Purpose
`--jinja`	—	Enable Jinja2 chat template rendering (required for custom template)
`--reasoning`	`on`	Enable reasoning/thinking output
`--reasoning-format`	`deepseek-legacy`	Use DeepSeek-style reasoning format
`-ngl`	`99`	Offload all layers to GPU

About Nex-N2-mini

Nex-N2-mini is an agentic model with Agentic Thinking — a framework that unifies reasoning, tool use, and environment execution:

Adaptive Thinking: The model decides when and how deeply to think
Coherent Thinking: Consistent reasoning paradigm across tasks and modalities

Built on Qwen3.5-35B-A3B-Base (MoE architecture, 35B total / 3B active parameters).

For more information, see the original model card: nex-agi/Nex-N2-mini

License

Apache-2.0 (same as the original model)

Downloads last month: 668

GGUF

Model size

35B params

Architecture

qwen35moe

Hardware compatibility

8-bit

Model tree for hendrik289/Nex-N2-mini-Q8_0-GGUF

Base model

nex-agi/Nex-N2-mini

Quantized

(35)

this model