Instructions to use Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF",
	filename="Llama-3.2-3B-MoE-4Expert.BF16.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 Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF:BF16
# Run inference directly in the terminal:
llama-cli -hf Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF:BF16

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 Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF:BF16
# Run inference directly in the terminal:
./llama-cli -hf Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF:BF16

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 Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF:BF16

Use Docker

docker model run hf.co/Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF:BF16

LM Studio
Jan

vLLM

How to use Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-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": "Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF:BF16

Ollama
How to use Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF with Ollama:
```
ollama run hf.co/Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF:BF16
```

Unsloth Studio

How to use Fu01978/Llama-3.2-3B-MoE-4Expert-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 Fu01978/Llama-3.2-3B-MoE-4Expert-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 Fu01978/Llama-3.2-3B-MoE-4Expert-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 Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF to start chatting

How to use Fu01978/Llama-3.2-3B-MoE-4Expert-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-server -hf Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF:BF16

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": "Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use Fu01978/Llama-3.2-3B-MoE-4Expert-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-server -hf Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF:BF16

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 Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF:BF16

Run Hermes

hermes

Atomic Chat new
Docker Model Runner
How to use Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF with Docker Model Runner:
```
docker model run hf.co/Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF:BF16
```

Lemonade

How to use Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF:BF16

Run and chat with the model

lemonade run user.Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF-BF16

List all available models

lemonade list

Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF

Quantized GGUF versions of Fu01978/Llama-3.2-3B-MoE-4Expert for efficient local inference with llama.cpp and compatible tools.

Model Description

This repository contains GGUF quantizations of a 4-expert MoE model specializing in:

General chat & explanations
Code & programming
Creative writing
Mathematics

For full model details, see the original model card.

Available Files

Quant Type	Size	Use Case
BF16	19.1 GB	Maximum quality, high VRAM
Q4_K_M	5.86 GB	Best balance of quality/size

Quantization Details

BF16: Full precision GGUF format - identical quality to original model
Q4_K_M: 4-bit quantization with medium quality - recommended for most users

Usage

llama.cpp

# Download the model
huggingface-cli download Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF Llama-3.2-3B-MoE-4Expert.Q4_K_M.gguf --local-dir .

# Run with llama.cpp
./llama-cli -m Llama-3.2-3B-MoE-4Expert.Q4_K_M.gguf -p "Write a Python function to reverse a string" -n 512

Python (llama-cpp-python)

from llama_cpp import Llama

llm = Llama(
    model_path="Llama-3.2-3B-MoE-4Expert.Q4_K_M.gguf",
    n_ctx=2048,
    n_threads=8,
)

output = llm(
    "Explain quantum entanglement in simple terms",
    max_tokens=512,
    temperature=0.7,
)
print(output['choices'][0]['text'])

Performance Notes

The Q4_K_M quantization provides excellent quality with minimal degradation compared to the original model while using ~65% less disk space and memory. Recommended for most use cases. The BF16 version maintains full original quality and is recommended if you have sufficient VRAM/RAM.

Conversion Details

Original Model: Fu01978/Llama-3.2-3B-MoE-4Expert
Conversion Tool: llama.cpp
Quantization Method: Q4_K_M via llama.cpp quantization — BF16 via llama.cpp convert_hf_to_gguf.py script

Acknowledgments

Original MoE model by Fu01978
GGUF conversion using llama.cpp
Base models: Meta AI (Llama 3.2), unsloth, prithivMLmods, DavidAU

Downloads last month: 10

GGUF

Model size

10B params

Architecture

llama

Hardware compatibility

4-bit

16-bit

Model tree for Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF

Base model

Fu01978/Llama-3.2-3B-MoE-4Expert

Quantized

(3)

this model

Collection including Fu01978/Llama-3.2-3B-MoE-4Expert-Q4_K_M-GGUF

Quantizations

Collection

All GGUF quants that I have made so far, and demos too. • 6 items • Updated Mar 2