Instructions to use Fu01978/Llama-3.2-3B-MoE-4Expert 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 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Fu01978/Llama-3.2-3B-MoE-4Expert")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Fu01978/Llama-3.2-3B-MoE-4Expert")
model = AutoModelForCausalLM.from_pretrained("Fu01978/Llama-3.2-3B-MoE-4Expert")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Fu01978/Llama-3.2-3B-MoE-4Expert 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"
# 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",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

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

SGLang

How to use Fu01978/Llama-3.2-3B-MoE-4Expert with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "Fu01978/Llama-3.2-3B-MoE-4Expert" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Fu01978/Llama-3.2-3B-MoE-4Expert",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "Fu01978/Llama-3.2-3B-MoE-4Expert" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Fu01978/Llama-3.2-3B-MoE-4Expert",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Fu01978/Llama-3.2-3B-MoE-4Expert with Docker Model Runner:
```
docker model run hf.co/Fu01978/Llama-3.2-3B-MoE-4Expert
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Llama-3.2-3B-MoE-4Expert

A 4-expert Mixture of Experts (MoE) model built on unsloth/Llama-3.2-3B-Instruct, specializing in chat, code, creative writing, and mathematics.

Model Description

This model combines four specialized Llama-3.2-3B variants into a single MoE architecture that intelligently routes queries to the most appropriate expert:

General Chat & Explanations - Clear, structured responses for everyday queries
Code & Programming - Python development, algorithms, and optimization
Creative Writing - Stories, poetry, roleplay, and narrative content
Mathematics - Equations, proofs, calculus, and step-by-step solutions

Architecture

Base Model: unsloth/Llama-3.2-3B-Instruct
Gate Mode: cheap_embed (embedding-based routing)
Precision: bfloat16
Merge Method: mergekit-moe
Total Experts: 4

Expert Models

Expert	Model	Specialization
1	unsloth/Llama-3.2-3B-Instruct	General chat, summaries, explanations
2	prithivMLmods/Codepy-Deepthink-3B	Python, algorithms, debugging
3	DavidAU/Llama-3.2-3B-Instruct-heretic-ablitered-uncensored	Creative writing, fiction, roleplay
4	prithivMLmods/Llama-3.2-3B-Math-Oct	Mathematics, proofs, calculations

Usage

from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "Fu01978/Llama-3.2-3B-MoE-4Expert"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)

prompt = "Write a Python function to calculate fibonacci numbers"
inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(**inputs, max_new_tokens=512)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))