---
license: other
license_name: qwen-research
license_link: https://huggingface.co/Qwen/Qwen2.5-3B/blob/main/LICENSE
library_name: gguf
language:
  - ko
  - en
tags:
  - text-generation
  - korean
  - bilingual
  - qwen2
  - built-with-qwen
  - gguf
  - llama-cpp
  - quantized
  - imatrix
base_model: GuminiResearch/Gumini-1B-Base
quantized_by: Gumin Kwon
pipeline_tag: text-generation
---

# 🐻 Gumini-1B-Base-i1-GGUF (구미니)

<p align="center">
  <img src="https://img.shields.io/badge/Parameters-1.08B-blue" style="display:inline-block; margin-right:6px;" />
  <img src="https://img.shields.io/badge/Layers-10-green" style="display:inline-block; margin-right:6px;" />
  <img src="https://img.shields.io/badge/Format-GGUF-orange" style="display:inline-block; margin-right:6px;" />
  <img src="https://img.shields.io/badge/Quantization-imatrix-purple" style="display:inline-block; margin-right:6px;" />
  <img src="https://img.shields.io/badge/Built%20with-Qwen-purple" style="display:inline-block;" />
</p>

<p align="center">
  <a href="https://linkedin.com/in/devgumin" target="_blank">
    <img src="https://img.shields.io/badge/LinkedIn-Gumin%20Kwon-0A66C2?logo=linkedin&logoColor=white" style="display:inline-block; margin-right:6px;" />
  </a>

  <a href="https://x.com/Gumini_Research" target="_blank">
    <img src="https://img.shields.io/badge/X-@Gumini__Research-black?logo=x&logoColor=white" style="display:inline-block; margin-right:6px;" />
  </a>

  <a href="https://www.instagram.com/gumini_research/" target="_blank">
    <img src="https://img.shields.io/badge/Instagram-gumini__research-E4405F?logo=instagram&logoColor=white" style="display:inline-block;" />
  </a>
</p>

<p align="center"><b>Built with Qwen</b></p>

## Model Description

GGUF quantized versions of [GuminiResearch/Gumini-1B-Base](https://huggingface.co/GuminiResearch/Gumini-1B-Base) for use with [llama.cpp](https://github.com/ggerganov/llama.cpp) and compatible tools (Ollama, LM Studio, etc.).

All quantizations were created using **importance matrix (imatrix)** calibration for optimal quality preservation.

> This is a **BASE model**, not instruction-tuned.  
> It produces text continuations rather than conversational responses.

## Model Details

| Attribute | Value |
|-----------|-------|
| **Original Model** | [Gumini-1B-Base](https://huggingface.co/GuminiResearch/Gumini-1B-Base) |
| **Quantized by** | [Gumin Kwon (권구민)](https://linkedin.com/in/devgumin) |
| **Parameters** | 1.08B |
| **Layers** | 10 |
| **Hidden Size** | 2048 |
| **Base PPL (F16)** | 15.36 |

## Quantization Results

### Perplexity Comparison

![PPL Comparison](ppl_comparison.png)

### PPL vs Size Trade-off

![PPL vs Size](ppl_vs_size.png)

### Recommended Quantizations

| Quant | PPL | Size | PPL Δ | Quality | Use Case |
|-------|-----|------|-------|---------|----------|
| **Q8_0** | 15.40 | 1.1G | +0.03 | Excellent | Maximum quality |
| **Q6_K** | 15.43 | 852M | +0.07 | Excellent | High quality |
| **Q5_K_M** | 15.46 | 769M | +0.10 | Excellent | Balanced (recommended) |
| **Q4_K_M** | 15.61 | 691M | +0.25 | Very Good | Size optimized |
| **IQ4_XS** | 15.69 | 641M | +0.33 | Very Good | imatrix 4-bit |
| **IQ3_M** | 16.17 | 574M | +0.81 | Good | Mobile/Edge |

### All Quantization Results

![Quantization Results](quantization_results.png)

## Usage

### With llama.cpp

```bash
# Download
huggingface-cli download GuminiResearch/Gumini-1B-Base-i1-GGUF Gumini-1B-Base.i1-Q4_K_M.gguf

# Run
./llama-cli -m Gumini-1B-Base.i1-Q4_K_M.gguf -p "저는 구미니입니다." -n 100
```

### With Ollama

```bash
echo 'FROM ./Gumini-1B-Base.i1-Q4_K_M.gguf' > Modelfile
ollama create gumini-1b -f Modelfile
ollama run gumini-1b
```

### With LM Studio

1. Download any `.gguf` file from this repo
2. Import into LM Studio
3. Start generating!

## Quantization Guide

![Quantization Types Guide](quant_types_guide.png)

### Tips
- **Best quality**: Use Q8_0 or Q6_K
- **Balanced**: Use Q5_K_M or Q4_K_M
- **Mobile/Edge**: Use IQ4_XS or IQ3_M
- **"i1" prefix**: Indicates imatrix was used during quantization

## Original Model

**Gumini-1B** (구미니) is a bilingual Korean-English base language model created by inheriting the first 10 layers of **Qwen 2.5 3B** using the *Inheritune* methodology.

- **Training Method**: Inheritune + Pretraining
- **Tokens Trained**: ~393M tokens
- **Training Data**: 80% Korean, 20% English

See [GuminiResearch/Gumini-1B-Base](https://huggingface.co/GuminiResearch/Gumini-1B-Base) for full details.

## License

### Qwen Research License (Non-Commercial)

This model is **Built with Qwen** and derived from Qwen 2.5 3B.

```
Qwen is licensed under the Qwen RESEARCH LICENSE AGREEMENT.
Copyright (c) Alibaba Cloud. All Rights Reserved.
```

**This model is for NON-COMMERCIAL / RESEARCH use only.**  
For commercial use, contact Alibaba Cloud.

## Citation

```bibtex
@misc{gumini2025,
  title={Gumini-1B: Bilingual Language Model Built with Qwen via Inheritune},
  author={Gumin Kwon},
  year={2025},
  note={Built with Qwen},
  url={https://huggingface.co/GuminiResearch/Gumini-1B-Base-i1-GGUF}
}
```
## Author

**Gumin Kwon (권구민)**  
- 🔗 LinkedIn: https://linkedin.com/in/devgumin  
- 🤗 Hugging Face: https://huggingface.co/GuminiResearch  
- 𝕏 X (Twitter): https://x.com/Gumini_Research  
- 📸 Instagram: https://www.instagram.com/gumini_research/

---

<p align="center">
  <b>Built with Qwen</b><br>
  <i>Gumini - 작지만 똑똑한 AI</i>
</p>