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

Libraries

How to use PinkPixel/ASCII-Machine-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="PinkPixel/ASCII-Machine-GGUF",
	filename="ascii-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/ASCII-Machine-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/ASCII-Machine-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf PinkPixel/ASCII-Machine-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/ASCII-Machine-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama-cli -hf PinkPixel/ASCII-Machine-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/ASCII-Machine-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf PinkPixel/ASCII-Machine-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/ASCII-Machine-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf PinkPixel/ASCII-Machine-GGUF:Q4_K_M

Use Docker

docker model run hf.co/PinkPixel/ASCII-Machine-GGUF:Q4_K_M

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

Unsloth Studio new

How to use PinkPixel/ASCII-Machine-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/ASCII-Machine-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/ASCII-Machine-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/ASCII-Machine-GGUF to start chatting

Pi new

How to use PinkPixel/ASCII-Machine-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/ASCII-Machine-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/ASCII-Machine-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use PinkPixel/ASCII-Machine-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/ASCII-Machine-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/ASCII-Machine-GGUF:Q4_K_M

Run Hermes

hermes

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

Lemonade

How to use PinkPixel/ASCII-Machine-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull PinkPixel/ASCII-Machine-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.ASCII-Machine-GGUF-Q4_K_M

List all available models

lemonade list

✨ ASCII Machine GGUF ✨

Quantized versions of PinkPixel/ASCII-Machine

NOTE: This is the first version of this model and it may not always generate perfect ASCII art. Fine tuning is still in progress and there will be updated versions coming soon.

📦 Model Overview

This repository contains GGUF (llama.cpp) compatible versions of ASCII Machine, a specialized model for ASCII art generation based on Qwen3.5-2B.

Main Model: PinkPixel/ASCII-Machine
Architecture: Qwen3.5-2B
Trained in: Unsloth Studio
Dataset: PinkPixel/ASCII-Art

⚠️ Important Note: Vision Support

ASCII Machine features advanced vision-language capabilities. However, due to the very new architecture of Qwen3.5-2B, vision support (mmproj) may not yet be fully functional in current versions of llama.cpp, LM Studio, or Ollama.

We have included the mmproj.gguf files for experimentation, but expect updates as the ecosystem matures.

💾 Available Quantizations

File Name	Description
`ascii-machine.BF16.gguf`	Original Brain Float 16 precision
`ascii-machine.F16.gguf`	Half-precision Float 16
`ascii-machine.Q8_0.gguf`	8-bit quantization (High quality, large)
`ascii-machine.Q6_K.gguf`	6-bit quantization (Excellent balance)
`ascii-machine.Q5_K_M.gguf`	5-bit quantization (Recommended)
`ascii-machine.Q4_K_M.gguf`	4-bit quantization (Standard)
`ascii-machine.Q3_K_M.gguf`	3-bit quantization (Small)
`ascii-machine.Q2_K_L.gguf`	2-bit quantization (Extreme compression)
`ascii-machine.BF16-mmproj.gguf`	Vision adapter (Experimental)

💬 Example Usage

User:

Generate an ASCII rocket.

ASCII Machine:

   /\
  |  |
  |  |
 /____\
 [____]
  |  |
  |  |
 /_||_\

Made with ❤️ by Pink Pixel
"Dream it, Pixel it"

Downloads last month: 1,437

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/ASCII-Machine-GGUF

Base model

Qwen/Qwen3.5-2B-Base

Finetuned

Qwen/Qwen3.5-2B

Finetuned

unsloth/Qwen3.5-2B

Finetuned

PinkPixel/ASCII-Machine

Quantized

(1)

this model