Downloads · 30 days
738
20% of all-time downloads
INSAIT-Institute/BgGPT-Gemma-3-4B-IT-GGUF
BgGPT-Gemma-3-4B-IT-GGUF is a image-text-to-text model from INSAIT-Institute. Use it for the image-text-to-text task on the model card, and read the license before you ship it in a product. The card lists the license as gemma.
GGUF quantized versions of BgGPT-Gemma-3-4B-IT for use with llama.cpp, Ollama, LM Studio, and other GGUF-compatible tools. BgGPT 3.0 is a series of Bulgarian-adapted LLMs based on Gemma 3, developed by INSAIT.
Downloads · 30 days
738
20% of all-time downloads
All-time downloads
3.7K
Public
Repo size
12.6 GB
Likes
5
Public
Click a slice to open those files.
.gguf12.6 GB · 100%
From the Hugging Face model README
GGUF quantized versions of BgGPT-Gemma-3-4B-IT for use with llama.cpp, Ollama, LM Studio, and other GGUF-compatible tools. BgGPT 3.0 is a series of Bulgarian-adapted LLMs based on Gemma 3, developed by INSAIT.
Blog post: BgGPT-3 Release
| Filename | Quant type | Description |
|---|---|---|
BgGPT-Gemma-3-4B-IT-Q4_K_M.gguf | Q4_K_M | Good balance of quality and size — recommended |
BgGPT-Gemma-3-4B-IT-Q5_K_M.gguf | Q5_K_M | High quality, slightly larger |
BgGPT-Gemma-3-4B-IT-Q6_K.gguf | Q6_K | Very high quality, near lossless |
BgGPT-Gemma-3-4B-IT-Q8_0.gguf | Q8_0 | Essentially lossless |
# Download a specific quantization
huggingface-cli download INSAIT-Institute/BgGPT-Gemma-3-4B-IT-GGUF \
--include "BgGPT-Gemma-3-4B-IT-Q4_K_M.gguf" \
--local-dir .
# Run with llama-cli
llama-cli -m BgGPT-Gemma-3-4B-IT-Q4_K_M.gguf \
-p "Кога е основан Софийският университет?" \
-n 512
Create a Modelfile:
FROM ./BgGPT-Gemma-3-4B-IT-Q4_K_M.gguf
Then:
ollama create bggpt-gemma3-4b -f Modelfile
ollama run bggpt-gemma3-4b
Search for BgGPT-Gemma-3-4B-IT-GGUF in the model browser, or download a GGUF file manually and load it.
# Download all quantizations
huggingface-cli download INSAIT-Institute/BgGPT-Gemma-3-4B-IT-GGUF
# Download a specific file
huggingface-cli download INSAIT-Institute/BgGPT-Gemma-3-4B-IT-GGUF \
--include "BgGPT-Gemma-3-4B-IT-Q4_K_M.gguf" \
--local-dir .
<!-- TODO: Add benchmarks, evaluation, citation -->
BgGPT-Gemma-3-4B-IT-GGUF is distributed under the Gemma Terms of Use.