Instructions to use PinkPixel/Purlie-2B-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PinkPixel/Purlie-2B-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="PinkPixel/Purlie-2B-GGUF",
	filename="Purlie-2B.BF16-mmproj.gguf",
)

llm.create_chat_completion(
	messages = "\"Меня зовут Вольфганг и я живу в Берлине\""
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

How to use PinkPixel/Purlie-2B-GGUF with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf PinkPixel/Purlie-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf PinkPixel/Purlie-2B-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf PinkPixel/Purlie-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf PinkPixel/Purlie-2B-GGUF:Q4_K_M

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 PinkPixel/Purlie-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf PinkPixel/Purlie-2B-GGUF:Q4_K_M

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 PinkPixel/Purlie-2B-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PinkPixel/Purlie-2B-GGUF:Q4_K_M

Use Docker

docker model run hf.co/PinkPixel/Purlie-2B-GGUF:Q4_K_M

LM Studio
Jan
Ollama
How to use PinkPixel/Purlie-2B-GGUF with Ollama:
```
ollama run hf.co/PinkPixel/Purlie-2B-GGUF:Q4_K_M
```

Unsloth Studio new

How to use PinkPixel/Purlie-2B-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 PinkPixel/Purlie-2B-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 PinkPixel/Purlie-2B-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for PinkPixel/Purlie-2B-GGUF to start chatting

Pi new

How to use PinkPixel/Purlie-2B-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf PinkPixel/Purlie-2B-GGUF:Q4_K_M

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": "PinkPixel/Purlie-2B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use PinkPixel/Purlie-2B-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 PinkPixel/Purlie-2B-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 PinkPixel/Purlie-2B-GGUF:Q4_K_M

Run Hermes

hermes

Docker Model Runner
How to use PinkPixel/Purlie-2B-GGUF with Docker Model Runner:
```
docker model run hf.co/PinkPixel/Purlie-2B-GGUF:Q4_K_M
```

Lemonade

How to use PinkPixel/Purlie-2B-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PinkPixel/Purlie-2B-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Purlie-2B-GGUF-Q4_K_M

List all available models

lemonade list

✨ Purlie-2B GGUF: The Crochet Translation Model ✨

This repository contains GGUF quantizations of Purlie-2B, a specialized multimodal vision-language model fine-tuned for the crochet community. It excels at translating Vietnamese crochet patterns into standard English terminology and can extract pattern instructions directly from images.

Original Model: PinkPixel/Purlie-2B

📦 Available GGUF Files

File Name	Size	Description
Purlie-2B.BF16.gguf	3.6 GB	Original BFloat16 precision (Recommended for accuracy)
Purlie-2B.F16.gguf	3.6 GB	standard Float16 precision
Purlie-2B.Q8_0.gguf	1.9 GB	8-bit quantization (High quality, lower VRAM)
Purlie-2B.Q6_K.gguf	1.5 GB	6-bit quantization
Purlie-2B.Q5_K_M.gguf	1.4 GB	5-bit quantization (Balanced)
Purlie-2B.Q4_K_M.gguf	1.2 GB	4-bit quantization (Optimized for speed/size)
Purlie-2B.Q3_K_M.gguf	1.1 GB	3-bit quantization
Purlie-2B.Q2_K_L.gguf	1.1 GB	2-bit quantization (Lowest VRAM)
Purlie-2B.BF16-mmproj.gguf	641 MB	Multimodal projector (Required for vision tasks)

🚀 Key Features

🇻🇳 Vietnamese to 🇺🇸 English Translation: Translates technical crochet terms and abbreviations.
🖼️ Image-to-Pattern Extraction: Recognizes crochet patterns within images and converts them to structured text.
🧶 Technical Expertise: Understands specific techniques like BLO, FLO, MR, and complex stitch combinations.
💻 Local Inference: Use with llama.cpp, LM Studio, Jan, or other GGUF-compatible runners.

📊 Example Usage

Text Translation (Vietnamese to English)

Prompt:

Dịch đoạn mã móc len sau sang tiếng Anh: Hàng 1: MR, 6 mũi móc đơn (6) Hàng 2: 6 mũi tăng (12) Hàng 3: (1 mũi móc đơn, 1 mũi tăng) x 6 (18)

Purlie-2B Response:

Row 1: MR, 6 single crochet (6) Row 2: 6 increase (12) Row 3: (1 single crochet, 1 increase) x 6 (18)

🛠️ How to Use with llama.cpp

To run the vision capabilities, you need both the main model and the mmproj file:

./llama-qwen2-vl-cli \
    -m Purlie-2B.Q4_K_M.gguf \
    --mmproj Purlie-2B.BF16-mmproj.gguf \
    --image pattern_test_image.jpg \
    -p "Dịch sơ đồ móc len trong ảnh sang tiếng Anh chuẩn."

📜 License

This model is licensed under the Apache 2.0 License. See the LICENSE file for details.

💖 Credits & Support

Made with ❤️ by Pink Pixel

Website: pinkpixel.dev
GitHub: github.com/pinkpixel-dev
Buy me a coffee: Coffee Link

Dream it, Pixel it ✨

Downloads last month: 831

GGUF

Model size

2B params

Architecture

qwen35

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Collection including PinkPixel/Purlie-2B-GGUF

GGUFS

Collection

7 items • Updated 5 days ago