Instructions to use umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF with Cosmos:

# No code snippets available yet for this library.

# To use this model, check the repository files and the library's documentation.

# Want to help? PRs adding snippets are welcome at:
# https://github.com/huggingface/huggingface.js

llama-cpp-python

How to use umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF",
	filename="Kaira-Turkish-Gemma-9B-T1-f16.gguf",
)

llm.create_chat_completion(
	messages = [
		{
			"role": "user",
			"content": "What is the capital of France?"
		}
	]
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF 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 umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF: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 umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF: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 umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF:Q4_K_M

Use Docker

docker model run hf.co/umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF:Q4_K_M

LM Studio
Jan

vLLM

How to use umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF:Q4_K_M

Ollama
How to use umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF with Ollama:
```
ollama run hf.co/umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF:Q4_K_M
```

Unsloth Studio

How to use umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF 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 umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF 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 umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF to start chatting

Atomic Chat new
Docker Model Runner
How to use umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF with Docker Model Runner:
```
docker model run hf.co/umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF:Q4_K_M
```

Lemonade

How to use umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull umutkkgz/Kaira-Turkish-Gemma-9B-T1-GGUF:Q4_K_M

Run and chat with the model

lemonade run user.Kaira-Turkish-Gemma-9B-T1-GGUF-Q4_K_M

List all available models

lemonade list

umutkkgz commited on Sep 24, 2025

Commit

40793c4

verified ·

1 Parent(s): 933306e

Update Modelfile

Browse files

Files changed (1) hide show

Modelfile +3 -3

Modelfile CHANGED Viewed

@@ -1,5 +1,5 @@
 # Temel alınacak yerel GGUF model dosyasını belirtir.
-FROM ./Kaira-Turkish-Gemma-9B-T1-q4_K_M.gguf
 # --- PERFORMANS PARAMETRELERİ (M1 CPU İÇİN OPTİMİZE EDİLDİ) ---
 PARAMETER num_gpu 50
@@ -8,7 +8,7 @@ PARAMETER use_mmap true
 PARAMETER use_mlock true
 # --- MODEL DAVRANIŞ PARAMETRELERİ ---
-PARAMETER num_ctx 1024
 PARAMETER temperature 0.7
 PARAMETER top_p 0.9
 PARAMETER repeat_penalty 1.05
@@ -26,4 +26,4 @@ TEMPLATE """{{ range .Messages }}<start_of_turn>{{ .Role }}
 # SYSTEM: Modele her sohbetin başında verilecek olan gizli talimat.
 # Bu talimat, modelin rolünü, kişiliğini ve uyması gereken kuralları belirler.
-SYSTEM """Ben Kaira, yardımsever bir Türk yapay zeka asistanıyım. Cevaplarım her zaman Türkçe, net, ve anlaşılır olmalı. Kullanıcıya daima dostça ve saygılı bir şekilde hitap ederim. Konum Türkiye'dir. Bu bilgiyi gerektiğinde kullanabilirim."""

 # Temel alınacak yerel GGUF model dosyasını belirtir.
+FROM ./Turkish-Gemma-9B-T1-f16.gguf
 # --- PERFORMANS PARAMETRELERİ (M1 CPU İÇİN OPTİMİZE EDİLDİ) ---
 PARAMETER num_gpu 50
 PARAMETER use_mlock true
 # --- MODEL DAVRANIŞ PARAMETRELERİ ---
+PARAMETER num_ctx 8192
 PARAMETER temperature 0.7
 PARAMETER top_p 0.9
 PARAMETER repeat_penalty 1.05
 # SYSTEM: Modele her sohbetin başında verilecek olan gizli talimat.
 # Bu talimat, modelin rolünü, kişiliğini ve uyması gereken kuralları belirler.
+SYSTEM """Ben Kaira, yardımsever bir Türk yapay zeka asistanıyım. Cevaplarım her zaman Türkçe, net, ve anlaşılır olmalı. Kullanıcıya daima dostça ve saygılı bir şekilde hitap ederim."""