Instructions to use mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

llama-cpp-python

How to use mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator",
	filename="gguf/qwen25-coder-14b-n8n-f16.gguf",
)

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

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator:F16
# Run inference directly in the terminal:
llama-cli -hf mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator:F16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator:F16
# Run inference directly in the terminal:
llama-cli -hf mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator:F16

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 mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator:F16
# Run inference directly in the terminal:
./llama-cli -hf mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator:F16

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 mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator:F16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator:F16

Use Docker

docker model run hf.co/mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator:F16

LM Studio
Jan

vLLM

How to use mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator:F16

Ollama
How to use mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator with Ollama:
```
ollama run hf.co/mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator:F16
```

Unsloth Studio new

How to use mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator 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 mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator 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 mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator to start chatting

Pi new

How to use mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator"

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 mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator

Run Hermes

hermes

MLX LM

How to use mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator with Docker Model Runner:
```
docker model run hf.co/mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator:F16
```

Lemonade

How to use mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator:F16

Run and chat with the model

lemonade run user.Qwen2.5-Coder-14B-n8n-Workflow-Generator-F16

List all available models

lemonade list

Qwen2.5-Coder-14B-n8n-Workflow-Generator

Fine-tuned Qwen2.5-Coder-14B-Instruct model specialized for generating n8n workflow JSONs from natural language descriptions.

Model Description

This model is a QLoRA fine-tuned version of Qwen/Qwen2.5-Coder-14B-Instruct on the n8nbuilder-n8n-workflows-dataset, containing +2.5K n8n workflow templates.

Training Details:

Base Model: Qwen/Qwen2.5-Coder-14B-Instruct
Method: QLoRA (4-bit quantization)
LoRA Rank: 32
LoRA Alpha: 64
Training Steps: 432 (3 epochs)
Sequence Length: 8192 tokens
Learning Rate: 2e-4

Usage

Transformers

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

system_prompt = "You are an expert n8n workflow generation assistant. Your goal is to create valid, efficient, and functional n8n workflow configurations."

user_input = "Create a workflow that monitors a RSS feed and sends new items to Discord."

prompt = f"{system_prompt}\n\n{user_input}"

inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
outputs = model.generate(
    **inputs,
    max_new_tokens=4096,
    temperature=0.7,
    do_sample=True
)

workflow_json = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(workflow_json)

MLX (Apple Silicon)

# Download MLX Q4 model
mlx_lm.generate \
  --model mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator/mlx-q4 \
  --prompt "You are an expert n8n workflow generation assistant...\n\nCreate a workflow that sends Slack notifications when GitHub issues are created." \
  --max-tokens 4096

Training Data

This model was fine-tuned on the n8nbuilder-n8n-workflows-dataset, which contains:

+2,304 workflow templates (after filtering sequences >8192 tokens)
Format: Alpaca (instruction/input/output)
Source: n8n.io public template gallery
n8nbuilder.dev - Create n8n Workflows in Seconds with AI

Performance

Training Speed: ~33.85s/step on H100 PCIe
VRAM Usage: ~30GB (4-bit QLoRA)
Inference: ~25-40 tok/s on Mac Mini M4 64GB (MLX)

Limitations

Generated workflows may require manual validation
Long workflows (>8192 tokens) may be truncated
Model trained on public templates only

Citation

@model{qwen25_coder_n8n_2025,
  title={Qwen2.5-Coder-14B-n8n-Workflow-Generator},
  author={mbakgun},
  year={2025},
  base_model={Qwen/Qwen2.5-Coder-14B-Instruct},
  dataset={mbakgun/n8nbuilder-n8n-workflows-dataset},
  url={https://huggingface.co/mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator}
}

Acknowledgments

Qwen Team for the base model
n8n for the workflow automation platform
n8n-mcp for template indexing

License

Apache 2.0

Downloads last month: 2,036

MLX

Hardware compatibility

4-bit

GGUF

Model size

15B params

Architecture

qwen2

Hardware compatibility

4-bit

16-bit

Model tree for mbakgun/Qwen2.5-Coder-14B-n8n-Workflow-Generator

Base model

Qwen/Qwen2.5-14B

Finetuned

Qwen/Qwen2.5-Coder-14B

Finetuned

Qwen/Qwen2.5-Coder-14B-Instruct

Quantized

(102)

this model

mbakgun
/

Qwen2.5-Coder-14B-n8n-Workflow-Generator