Instructions to use distil-labs/distil-email-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use distil-labs/distil-email-classifier with Transformers:

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

pipe = pipeline("text-generation", model="distil-labs/distil-email-classifier")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("distil-labs/distil-email-classifier")
model = AutoModelForCausalLM.from_pretrained("distil-labs/distil-email-classifier")
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]:]))

llama-cpp-python

How to use distil-labs/distil-email-classifier with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="distil-labs/distil-email-classifier",
	filename="model.gguf",
)

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

Inference
Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use distil-labs/distil-email-classifier with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf distil-labs/distil-email-classifier
# Run inference directly in the terminal:
llama-cli -hf distil-labs/distil-email-classifier

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf distil-labs/distil-email-classifier
# Run inference directly in the terminal:
llama-cli -hf distil-labs/distil-email-classifier

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 distil-labs/distil-email-classifier
# Run inference directly in the terminal:
./llama-cli -hf distil-labs/distil-email-classifier

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 distil-labs/distil-email-classifier
# Run inference directly in the terminal:
./build/bin/llama-cli -hf distil-labs/distil-email-classifier

Use Docker

docker model run hf.co/distil-labs/distil-email-classifier

LM Studio
Jan

vLLM

How to use distil-labs/distil-email-classifier with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/distil-labs/distil-email-classifier

SGLang

How to use distil-labs/distil-email-classifier 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 "distil-labs/distil-email-classifier" \
    --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": "distil-labs/distil-email-classifier",
		"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 "distil-labs/distil-email-classifier" \
        --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": "distil-labs/distil-email-classifier",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use distil-labs/distil-email-classifier with Ollama:
```
ollama run hf.co/distil-labs/distil-email-classifier
```

Unsloth Studio new

How to use distil-labs/distil-email-classifier 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 distil-labs/distil-email-classifier 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 distil-labs/distil-email-classifier to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for distil-labs/distil-email-classifier to start chatting

Pi new

How to use distil-labs/distil-email-classifier with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf distil-labs/distil-email-classifier

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": "distil-labs/distil-email-classifier"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use distil-labs/distil-email-classifier with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf distil-labs/distil-email-classifier

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 distil-labs/distil-email-classifier

Run Hermes

hermes

Docker Model Runner
How to use distil-labs/distil-email-classifier with Docker Model Runner:
```
docker model run hf.co/distil-labs/distil-email-classifier
```

Lemonade

How to use distil-labs/distil-email-classifier with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull distil-labs/distil-email-classifier

Run and chat with the model

lemonade run user.distil-email-classifier-{{QUANT_TAG}}

List all available models

lemonade list

We fine-tuned an email classification model so you can auto-label your emails locally with n8n.

We built a fully local Gmail auto-labeler with n8n + a fine-tuned 0.6B model (no email content sent to cloud LLMs)

Most of our inboxes are a mix of useful and distracting. Labels can help making order from the chaos - but labelling all emails manually takes time too.

We put together a setup that auto-labels Gmail locally, so email content does not go to external LLM APIs.

What it does (end-to-end local):

n8n trigger when you receive an email
It sends the email text (subject + snippet/body) to a fine-tuned model running on localhost via Ollama
It applies the predicted label back in Gmail (we recommend prefixing labels with AI/)

Label set (10-way closed set):

Billing, Newsletter, Work, Personal, Promotional, Security, Shipping, Travel, Spam, Other

Results:

Model	Accuracy
Teacher (GPT-OSS-120B)	93%
Base student (Qwen3-0.6B)	38%
Fine-tuned student (Qwen3-0.6B)	93%

Traning setup

Student model	Qwen3-0.6B (600M parameters)
Teacher model	GPT-OSS-120B
Training method	Knowledge distillation + supervised fine-tuning (SFT)
Seed data	154 examples
Training data	10,000 synthetic email examples across 10 categories generated using our data synthesis pipeline

System Setup

Installation Steps:

Install n8n locally

# Install Node.js (if not installed)
brew install node

# Install n8n globally
npm install -g n8n

# Start n8n
n8n

Access n8n at: http://localhost:5678

Download the model

#install huggingface CLI if not instlalled 
python3 -m pip install -U huggingface_hub

#download the model
hf download distil-labs/distil-email-classifier --local-dir ./distil-email-classifier

Run the model

#install Ollama or you can download from https://ollama.com/download
brew install ollama 

#start Ollama
ollama serve

#navigate to your model folder
cd ./distil-email-classifier

#create model in ollama 
ollama create email-classifier -f Modelfile

#verify the model is created or not 
ollama list

#run the model
ollama run email-classifier "test"

#check the model is running or not
ollama ps

Expected output:

NAME                       ID              SIZE      PROCESSOR    CONTEXT    UNTIL              
email-classifier:latest    695190b0f07f    3.5 GB    100% GPU     4096       4 minutes from now

#to keep model running forver run the below commands
OLLAMA_KEEP_ALIVE=-1 ollama run email-classifier "test"

Now shows Forever instead of 4 minutes from now.

Once you finish the setup, open n8n in your browser (http://localhost:5678), sign up with your email, and you get an access code from n8n for your email, you can update the access code.

Import n8n workflows

Download the workflow JSON files from our GitHub repository: https://github.com/distil-labs/distil-n8n-gmail-automation

Two workflows are available:

Real-time Classification: Triggers automatically on each incoming email
Batch Processing: Classifies multiple existing emails at once

To connect your Gmail you need to setup Gmail OAuth (Google cloud console) you can find detailed steps on this on github readme.

Before running the workflow, create all 10 labels manually in your Gmail account. Use the "AI/" prefix to match the model output (AI/Billing, AI/Work, AI/Travel, and so on).

Once this is running, New messages get labeled automatically.

If you want different labels, you can distill a custom version of this classifier on the distil labs platform. When you sign up, you get two free training credits to train the model.

Full Write up: https://www.distillabs.ai/blog/building-a-local-agent-for-email-classification-using-n8n-distil-labs

workflows: https://github.com/distil-labs/distil-n8n-gmail-automation

Model: https://huggingface.co/distil-labs/distil-email-classifier