Instructions to use EllaPriest45/Nanbeige4.2-3B_Heretic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use EllaPriest45/Nanbeige4.2-3B_Heretic with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf EllaPriest45/Nanbeige4.2-3B_Heretic:Q8_0
# Run inference directly in the terminal:
llama cli -hf EllaPriest45/Nanbeige4.2-3B_Heretic:Q8_0

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf EllaPriest45/Nanbeige4.2-3B_Heretic:Q8_0
# Run inference directly in the terminal:
llama cli -hf EllaPriest45/Nanbeige4.2-3B_Heretic: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 EllaPriest45/Nanbeige4.2-3B_Heretic:Q8_0
# Run inference directly in the terminal:
./llama-cli -hf EllaPriest45/Nanbeige4.2-3B_Heretic: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 EllaPriest45/Nanbeige4.2-3B_Heretic:Q8_0
# Run inference directly in the terminal:
./build/bin/llama-cli -hf EllaPriest45/Nanbeige4.2-3B_Heretic:Q8_0

Use Docker

docker model run hf.co/EllaPriest45/Nanbeige4.2-3B_Heretic:Q8_0

LM Studio
Jan
Ollama
How to use EllaPriest45/Nanbeige4.2-3B_Heretic with Ollama:
```
ollama run hf.co/EllaPriest45/Nanbeige4.2-3B_Heretic:Q8_0
```

Unsloth Studio

How to use EllaPriest45/Nanbeige4.2-3B_Heretic 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 EllaPriest45/Nanbeige4.2-3B_Heretic 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 EllaPriest45/Nanbeige4.2-3B_Heretic to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for EllaPriest45/Nanbeige4.2-3B_Heretic to start chatting

How to use EllaPriest45/Nanbeige4.2-3B_Heretic with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf EllaPriest45/Nanbeige4.2-3B_Heretic: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": "EllaPriest45/Nanbeige4.2-3B_Heretic:Q8_0"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use EllaPriest45/Nanbeige4.2-3B_Heretic with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf EllaPriest45/Nanbeige4.2-3B_Heretic: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 EllaPriest45/Nanbeige4.2-3B_Heretic:Q8_0

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use EllaPriest45/Nanbeige4.2-3B_Heretic with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf EllaPriest45/Nanbeige4.2-3B_Heretic:Q8_0

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "EllaPriest45/Nanbeige4.2-3B_Heretic:Q8_0" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

Docker Model Runner
How to use EllaPriest45/Nanbeige4.2-3B_Heretic with Docker Model Runner:
```
docker model run hf.co/EllaPriest45/Nanbeige4.2-3B_Heretic:Q8_0
```

Lemonade

How to use EllaPriest45/Nanbeige4.2-3B_Heretic with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull EllaPriest45/Nanbeige4.2-3B_Heretic:Q8_0

Run and chat with the model

lemonade run user.Nanbeige4.2-3B_Heretic-Q8_0

List all available models

lemonade list

YAML Metadata Warning:empty or missing yaml metadata in repo card

Check out the documentation for more information.

Hi just making a mirror of Nanbeige 4.2 3-B Heretic.

Its an AI agent that runs easily on most configurations. It has good performance.

Its the heretic version aka the censorship is heavily cut down.

Theres two versions, the full original version, you download all the files EXCEPT the GGUF.

Then you got the Q8 GGUF version, you only need that one file.

Downloads last month: 181

Safetensors

Model size

4B params

Tensor type

BF16

Inference Providers NEW

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