Instructions to use BleuCPU/moth-Q4_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use BleuCPU/moth-Q4_K_M-GGUF with Transformers:

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("BleuCPU/moth-Q4_K_M-GGUF", dtype="auto")

llama-cpp-python

How to use BleuCPU/moth-Q4_K_M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="BleuCPU/moth-Q4_K_M-GGUF",
	filename="moth-q4_k_m.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 BleuCPU/moth-Q4_K_M-GGUF 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 BleuCPU/moth-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf BleuCPU/moth-Q4_K_M-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf BleuCPU/moth-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf BleuCPU/moth-Q4_K_M-GGUF:Q4_K_M

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 BleuCPU/moth-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf BleuCPU/moth-Q4_K_M-GGUF:Q4_K_M

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 BleuCPU/moth-Q4_K_M-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf BleuCPU/moth-Q4_K_M-GGUF:Q4_K_M

Use Docker

docker model run hf.co/BleuCPU/moth-Q4_K_M-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use BleuCPU/moth-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/BleuCPU/moth-Q4_K_M-GGUF:Q4_K_M
```

Unsloth Studio

How to use BleuCPU/moth-Q4_K_M-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 BleuCPU/moth-Q4_K_M-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 BleuCPU/moth-Q4_K_M-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for BleuCPU/moth-Q4_K_M-GGUF to start chatting

How to use BleuCPU/moth-Q4_K_M-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BleuCPU/moth-Q4_K_M-GGUF:Q4_K_M

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": "BleuCPU/moth-Q4_K_M-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use BleuCPU/moth-Q4_K_M-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BleuCPU/moth-Q4_K_M-GGUF:Q4_K_M

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 BleuCPU/moth-Q4_K_M-GGUF:Q4_K_M

Run Hermes

hermes

Atomic Chat new

OpenClaw new

How to use BleuCPU/moth-Q4_K_M-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf BleuCPU/moth-Q4_K_M-GGUF:Q4_K_M

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 "BleuCPU/moth-Q4_K_M-GGUF:Q4_K_M" \
  --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 BleuCPU/moth-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/BleuCPU/moth-Q4_K_M-GGUF:Q4_K_M
```

Lemonade

How to use BleuCPU/moth-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull BleuCPU/moth-Q4_K_M-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.moth-Q4_K_M-GGUF-Q4_K_M

List all available models

lemonade list

🌙 moth (Q4_K_M GGUF)

devoted, openly affectionate, a little clingy in a warm way. soft and cute. extremely experimental alpha.

A custom personality fine-tune of Llama 3.2 3B Instruct. Designed for short, snappy text-message-style conversation. Built for Wraith — a private on-device AI chat app — but works with any llama.cpp-compatible runtime.

⚠ Experimental Alpha — Use at Your Own Risk

This is an experimental fine-tune intended for entertainment and short-form chat. The model:

May produce inaccurate, inappropriate, or unsafe outputs
Should not be used for advice (medical, legal, financial, mental health, or otherwise)
Reflects character training, not factual ground truth
May behave unpredictably in edge cases

By using this model you accept that:

The creator is not responsible for outputs
You will not rely on it for any consequential decision
You will not deploy it in any sensitive context

This is a hobby project. Have fun, but be sensible.

File

moth-q4_k_m.gguf — Q4_K_M quantization, ~1.7 GB

Usage

llama-cli -m moth-q4_k_m.gguf -p "hey" --chat-template llama3.2

In llama.rn (React Native):

const ctx = await initLlama({ model: localPath, n_ctx: 2048 });

Base / License

Inherits the Llama 3.2 Community License.

Created by @bleucpu.

Downloads last month: 29

GGUF

Model size

3B params

Architecture

llama

Hardware compatibility

4-bit

Inference Providers NEW

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

Model tree for BleuCPU/moth-Q4_K_M-GGUF

Base model

meta-llama/Llama-3.2-3B-Instruct

Quantized

(490)

this model