LFM2.5-1.2B-Base-f16-GGUF

ko-fi github

LFM2.5-1.2B-f16-GGUF

1. Conversion tutorial (from .safetensors to .gguf)

1.1 Navigate to your base-model folder on your working directory and clone the base model

cd C:\models\base_models

git clone https://huggingface.co/Qwen/LFM2.5-1.2B

You must see config.json, model.safetensors, and tokenizer files in there.

1.3 Navigate to your working directory and clone the llama repository

cd C:\models\

git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp

the content of the conversion depency will be at C:\models\llama.cpp

1.4 Install the CORRECT dependencies for Hugging Face conversion

pip install -r requirements/requirements-convert_hf_to_gguf.txt

1.5 pre-compiled llama.cpp

Go to the official releases page: llama.cpp Releases

Look for the latest release and download the Windows .zip file (usually named something like llama-bXXXX-bin-win-vulcan-x64.zip or llama-...-bin-win-avx2-x64.zip).

You can also compile using C++ on Windows, which requires CMake and Visual Studio tools, but since I find easier to just download the pre-compiled .exe I did it like that

1.6 Move additional dependencies

Move the content unzipped folder and paste it directly into your C:\models\llama.cpp folder or where you set to download the item 1.3

1.7 Conversion run

Now, we run the Python script to translate the Hugging Face format into a raw 16-bit GGUF file. Make sure you are still inside the llama.cpp directory at your terminal.

python convert_hf_to_gguf.py "C:\models\base_models\LFM2.5-1.2B" --outtype f16 --outfile "C:\models\base_models\LFM2.5-1.2B\LFM2.5-1.2B-Base-f16.gguf"

---

Ronni Ross
2026