Instructions to use ngbcoder/flow-models-webdev-gguf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use ngbcoder/flow-models-webdev-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 ngbcoder/flow-models-webdev-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ngbcoder/flow-models-webdev-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 ngbcoder/flow-models-webdev-gguf:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf ngbcoder/flow-models-webdev-gguf:Q4_K_M

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf ngbcoder/flow-models-webdev-gguf:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama cli -hf ngbcoder/flow-models-webdev-gguf:Q4_K_M

Use Docker

docker model run hf.co/ngbcoder/flow-models-webdev-gguf:Q4_K_M

Llama new
LM Studio
Jan

vLLM

How to use ngbcoder/flow-models-webdev-gguf with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ngbcoder/flow-models-webdev-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": "ngbcoder/flow-models-webdev-gguf",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ngbcoder/flow-models-webdev-gguf:Q4_K_M

Ollama
How to use ngbcoder/flow-models-webdev-gguf with Ollama:
```
ollama run hf.co/ngbcoder/flow-models-webdev-gguf:Q4_K_M
```
Unsloth Desktop

How to use ngbcoder/flow-models-webdev-gguf with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ngbcoder/flow-models-webdev-gguf:Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "ngbcoder/flow-models-webdev-gguf:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use ngbcoder/flow-models-webdev-gguf with Docker Model Runner:
```
docker model run hf.co/ngbcoder/flow-models-webdev-gguf:Q4_K_M
```

Lemonade

How to use ngbcoder/flow-models-webdev-gguf with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull ngbcoder/flow-models-webdev-gguf:Q4_K_M

Run and chat with the model

lemonade run user.flow-models-webdev-gguf-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use ngbcoder/flow-models-webdev-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 ngbcoder/flow-models-webdev-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 ngbcoder/flow-models-webdev-gguf:Q4_K_M

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use ngbcoder/flow-models-webdev-gguf with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf ngbcoder/flow-models-webdev-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 "ngbcoder/flow-models-webdev-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"

flow-models-webdev-gguf / README.md

ngbcoder

Add Q4_K_M GGUF fine-tune and model card

6a88093 verified about 21 hours ago

preview code

Raw History Blame Contribute Delete

2.85 kB

metadata

base_model: unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit
library_name: unsloth
language:
  - en
license: llama3.2
tags:
  - llama
  - llama-3.2
  - gguf
  - unsloth
  - qlora
  - web-development
  - code
pipeline_tag: text-generation

Flow Models — Web Dev (Llama 3.2 3B Instruct, Q4_K_M)

A QLoRA fine-tune of Llama-3.2-3B-Instruct on a web-development instruction dataset, exported to GGUF for use with llama.cpp, Ollama, LM Studio, or any GGUF-compatible runtime.

Model details


Base model	`unsloth/Llama-3.2-3B-Instruct-unsloth-bnb-4bit`
Fine-tuning	QLoRA (4-bit), Unsloth
Export	Merged and quantized to Q4_K_M (1.88 GB)
Context length	2048
Language	English

Training

Hyperparameter	Value
LoRA rank / alpha	16 / 16
LoRA dropout	0
Target modules	`q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj`
Epochs	3
Batch size	2
Gradient accumulation	4
Learning rate	2e-4 (linear schedule)
Warmup steps	5
Weight decay	0.001
Optimizer	`adamw_8bit`
Max sequence length	2048
Packing	enabled
Seed	3407

Result: 87 steps, 1,376,556 tokens, training loss 1.20 → 0.39.

Dataset

formatted_webdev_dataset.json — 3,723 instruction/response examples covering HTML, CSS, JavaScript, Python, SQL, and general web development. Examples use the Alpaca prompt format and responses end with a [COMPLETE] marker.

Training text format:

Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.

### Instruction:
<instruction>

### Input:
<input>

### Response:
<response>
[COMPLETE]

Usage

llama.cpp

llama-cli -m Llama-3.2-3B-Instruct.Q4_K_M.gguf \
  -p "### Instruction:\nWrite a JavaScript function to count the number of vowels in a string.\n\n### Input:\n\n\n### Response:\n" \
  -n 256 --temp 0.2 -st

Ollama

ollama create flow-webdev -f Modelfile
ollama run flow-webdev

Expected output style

function countVowels(str) {
    let vowels = 'aeiou';
    let count = 0;
    for (let i = 0; i < str.length; i++) {
        if (vowels.includes(str[i].toLowerCase())) {
            count++;
        }
    }
    return count;
}
[COMPLETE]

Limitations

Trained on a relatively small, synthetic-style web-dev dataset; it can reproduce errors or outdated patterns from that data.
Best results come from the Alpaca prompt format it was trained on, not free-form chat.
The [COMPLETE] suffix is part of the learned response style.
Not evaluated for correctness, safety, or production use. Review generated code before running it.

License

Llama 3.2 Community License, inherited from the base model.