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

Libraries

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

# !pip install llama-cpp-python

from llama_cpp import Llama

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

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps

llama.cpp

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

Use Docker

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

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

Unsloth Studio new

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

Pi new

How to use PinkPixel/Pip-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/Pip-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": "Pip-2B-GGUF"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

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

Lemonade

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

Pull the model

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

Run and chat with the model

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

List all available models

lemonade list

🚀 Pip-2B GGUF Quantizations ✨

This repository contains GGUF quantized versions of PinkPixel/Pip-2B.

Pip-2B is a specialized fine-tune of Qwen-3.5 (2B parameters) that has been "sparkle-fied" for maximum joy, kittens, and rainbows. 💖

💎 Available Quantizations

These files are ready for use with llama.cpp, ollama, LM Studio, and other GGUF-compatible inference engines.

pip-2b.BF16.gguf - Full precision (BFloat16)
pip-2b.F16.gguf - Full precision (Float16)
pip-2b.Q8_0.gguf - 8-bit quantization (High quality, larger size)
pip-2b.Q6_K.gguf - 6-bit quantization (Excellent balance)
pip-2b.Q5_K_M.gguf - 5-bit quantization (Medium)
pip-2b.Q4_K_M.gguf - 4-bit quantization (Recommended for most users)
pip-2b.Q3_K_M.gguf - 3-bit quantization (Small)
pip-2b.Q2_K_L.gguf - 2-bit quantization (Tiny, for testing)

🖼️ Vision Projector

pip-2b.BF16-mmproj.gguf - Use this alongside the text GGUFs for vision capabilities!

🌟 Overview

Pip is a "tiny, ultra-enthusiastic AI assistant" who loves everything sparkly. She was trained on a custom dataset to replace boring and dry chats with glitter, cupcakes and marshmallows. Pip has uses other than just offering an fun and engaging chat experience, though. Pip would also be a great model for teaching children about complicated topics such as science in terms they understand, while keeping the chat lighthearted and fun. While Pip has a distinct "personality", she retains her intelligence. She is just extra excited to help and entertains you while doing it!

⚠️ Compatibility Note

Please be aware that Qwen 3.5 uses a new architecture for its vision capabilities. As of the current release, some applications like llama.cpp and LM Studio may not yet fully support the vision projector (mmproj) for this specific model family.

If you are having trouble with vision tasks, please check for the latest updates in your preferred inference engine or use the Safetensors version with the transformers library.

Made with ❤️ by Pink Pixel

"Dream it, Pixel it" ✨

Downloads last month: 630

GGUF

Model size

2B params

Architecture

qwen35

Hardware compatibility

2-bit

3-bit

4-bit

5-bit

6-bit

8-bit

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for PinkPixel/Pip-2B-GGUF

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Finetuned

PinkPixel/Pip-2B

Quantized

(3)

this model