Instructions to use Yacinedh/translategemma-4b-khutbah with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use Yacinedh/translategemma-4b-khutbah with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Yacinedh/translategemma-4b-khutbah:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Yacinedh/translategemma-4b-khutbah:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Yacinedh/translategemma-4b-khutbah:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf Yacinedh/translategemma-4b-khutbah:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf Yacinedh/translategemma-4b-khutbah:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf Yacinedh/translategemma-4b-khutbah:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf Yacinedh/translategemma-4b-khutbah:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf Yacinedh/translategemma-4b-khutbah:Q4_K_M

Use Docker

docker model run hf.co/Yacinedh/translategemma-4b-khutbah:Q4_K_M

LM Studio
Jan
Ollama
How to use Yacinedh/translategemma-4b-khutbah with Ollama:
```
ollama run hf.co/Yacinedh/translategemma-4b-khutbah:Q4_K_M
```

Unsloth Studio

How to use Yacinedh/translategemma-4b-khutbah with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Yacinedh/translategemma-4b-khutbah to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for Yacinedh/translategemma-4b-khutbah to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Yacinedh/translategemma-4b-khutbah to start chatting

Docker Model Runner
How to use Yacinedh/translategemma-4b-khutbah with Docker Model Runner:
```
docker model run hf.co/Yacinedh/translategemma-4b-khutbah:Q4_K_M
```

Lemonade

How to use Yacinedh/translategemma-4b-khutbah with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull Yacinedh/translategemma-4b-khutbah:Q4_K_M

Run and chat with the model

lemonade run user.translategemma-4b-khutbah-Q4_K_M

List all available models

lemonade list

Atomic Chat

TranslateGemma-4B-Khutbah

Arabic → German translation model specialized for Islamic sermons (khutbahs) — the compact sibling of Yacinedh/translategemma-12b-khutbah. Fine-tuned from google/translategemma-4b-it.

Headline: after domain fine-tuning, this 4B matches the stock 12B on the khutbah benchmark at 40% of the size — making it a strong choice for CPU/edge deployment (e.g. an offline fallback on a mosque laptop).

Results

74-case khutbah benchmark (embedding cosine vs held-out references, identical pipeline for all rows):

Model	Overall	Free sermon rhetoric
google/translategemma-4b-it (stock)	0.9368	0.8588
this model	0.9527	0.8789
google/translategemma-12b-it (stock, reference)	0.9535	0.8836

Training

Same recipe and data as the 12B: 24,240 Arabic–German pairs (four German Quran editions, liturgical formulas, hadith, terminology; benchmark sentences excluded), QLoRA r=16, lr 1e-4, 1 epoch. Trained on a single T4 (fp16). Code: MinbarAI/training.

Files

Merged fp16 safetensors
model-Q4_K_M.gguf (~2.5 GB) — runs on CPU via llama.cpp / Ollama

Usage

Identical to the 12B card — TranslateGemma structured chat template (source_lang_code: "ar", target_lang_code: "de-DE"). See Yacinedh/translategemma-12b-khutbah for snippets.

License

Gemma Terms of Use. Quran translation data from Tanzil via fawazahmed0/quran-api.

Downloads last month: 207

Safetensors

Model size

4B params

Tensor type

F16

Model tree for Yacinedh/translategemma-4b-khutbah

Base model

google/translategemma-4b-it

Quantized

(40)

this model