license, license_name, license_link, library_name, language, tags, base_model, quantized_by, pipeline_tag

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

🐻 Gumini-1B-Base-i1-GGUF (구미니)

Built with Qwen

Model Description

GGUF quantized versions of GuminiResearch/Gumini-1B-Base for use with 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
Quantized by	Gumin Kwon (권구민)
Parameters	1.08B
Layers	10
Hidden Size	2048
Base PPL (F16)	15.36

Quantization Results

Perplexity Comparison

PPL vs Size Trade-off

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

Usage

With llama.cpp

# 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

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

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 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

@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/

---

Built with Qwen
Gumini - 작지만 똑똑한 AI