---
license: apache-2.0
base_model: PinkPixel/ASCII-Machine
tags:
- ascii
- vision
- art
- unsloth
- gguf
- quantized
---
---
## 📦 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](https://huggingface.co/PinkPixel/ASCII-Machine)
- **Architecture:** Qwen3.5-2B
- **Trained in:** Unsloth Studio
- **Dataset:** [PinkPixel/ASCII-Art](https://huggingface.co/datasets/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:
```text
/\
| |
| |
/____\
[____]
| |
| |
/_||_\
```
---
